Programme

Please notice that the programme below may not reflect last minute changes.
For the most updated version, please visit COLING’2020 Underline platform.

All indicated times are in Central European Time (CET).

COLING’2020 has announced in the programme 16 papers that are deemed to be of outstanding quality. The selected papers are all on short-list for Best Paper, which will be revealed in the Closing Session. Outstanding papers are marked in this program with a star, .

Main conference program: download pdf version.

Relation of each paper from the Anthology with the COLING'2020 session where the Q&A will take place: Google Sheets, TSV, JSON.

Programme at a glance.

Birds of a feather sessions at a glance

Tuesday, December 8, 2020

14:00 - 14:30    Welcome and conference logistics - Room Poblenou

Donia Scott, COLING’2020 General Chair Joan Gómez Pallarès, Director General of Research of the Dept of Enterprises and Knowledge, Government of Catalonia. Júlia Miralles de Imperial, Deputy head for the area of Science and Universities, Barcelona City Council. Enric Vallduví, Vicerector for Research. Pompeu Fabra University. Leo Wanner, COLING’2020 Local Organization Committee Horacio Saggion, COLING’2020 Local Organization Committee Chengqing Zong and Núria Bel, COLING’2020 Program Co-Chairs Esther Seyffarth, COLING’2020 Virtual Social Chair

14:30 - 15:30    INVITED TALK 1 (live) - Room Poblenou Chair: ChuRen Huang

A multivariate multiple regression approach to the mental lexicon Harald Baayen Professor Seminar für Sprachwissenschaft Eberhard Karls Universität Tübingen

15:30 - 16:00    Session LONG1 - Language Modelling 1 - Room Montjuïc Chair: Fei Huang Co-Chair: Wenjuan Han

Exploring Controllable Text Generation Techniques Shrimai Prabhumoye1, Alan W Black1, Ruslan Salakhutdinov2 1Carnegie Mellon University, 2CMU

Infusing Sequential Information into Conditional Masked Translation Model with Self-Review Mechanism Pan Xie1, Zhi Cui2, Xiuying Chen3, XiaoHui Hu4, Jianwei Cui2, Bin Wang2 1+8613126899683, 2Xiaomi AI Lab, 3Peking University, 4Institute of Software, Chinese Academy of Sciences (ISCAS)

Building Hierarchically Disentangled Language Models for Text Generation with Named Entities Yash Agarwal1, Devansh Batra1, Ganesh Bagler2 1Netaji Subhas University of Technology, 2Indraprastha Institute of Information Technology Delhi (IIIT-Delhi)

CharBERT: Character-aware Pre-trained Language Model Wentao Ma1, Yiming Cui2, Chenglei Si3, Ting Liu2, Shijin Wang1, Guoping Hu1 1iFLYTEK Research, 2Harbin Institute of Technology, 3University of Maryland, College Park

A Graph Representation of Semi-structured Data for Web Question Answering xingyao zhang1, Linjun Shou2, Jian Pei3, Ming Gong4, Lijie Wen5, Daxin Jiang2 1, 2STCA NLP Group, Microsoft, 3Simon Fraser University, 4STCA NLP Group, Microsoft (China), 5School of Software, Tsinghua University

15:30 - 16:00    Session LONG2 - Information Extraction 1 - Room El Raval Chair: Carlos Ramisch Co-Chair: Lucia Donatelli

Catching Attention with Automatic Pull Quote Selection Tanner Bohn and Charles Ling Western University

MZET: Memory Augmented Zero-Shot Fine-grained Named Entity Typing Tao Zhang1, Congying Xia1, Chun-Ta Lu2, Philip Yu3 1University of Illinois at Chicago, 2Google, 3Universtiy of Illinois at Chicago

Span-based Joint Entity and Relation Extraction with Attention-based Span-specific and Contextual Semantic Representations bin ji, Jie Yu, Shasha Li, Jun Ma, Qingbo Wu, Yusong Tan, Huijun Liu college of computer, national university of defense technology

Hierarchical Chinese Legal event extraction via Pedal Attention Mechanism Shirong Shen, Guilin Qi, Zhen Li, Sheng Bi, Lusheng Wang Southeast University

Is Killed More Significant than Fled? A Contextual Model for Salient Event Detection Disha Jindal1, Daniel Deutsch2, Dan Roth2 1Google, 2University of Pennsylvania

15:30 - 16:00    Session POSTER1 - Sentiment and Emotion. Posters - Exhibition Room Vila Olímpica

Appraisal Theories for Emotion Classification in Text Jan Hofmann1, Enrica Troiano1, Kai Sassenberg2, Roman Klinger1 1University of Stuttgart, 2IWM Tübingen

A Symmetric Local Search Network for Emotion-Cause Pair Extraction Zifeng Cheng1, Zhiwei Jiang2, Yafeng Yin2, Hua Yu1, Qing Gu1 1Nanjing University, 2State Key Laboratory for Novel Software Technology, Nanjing University

Jointly Learning Aspect-Focused and Inter-Aspect Relations with Graph Convolutional Networks for Aspect Sentiment Analysis Bin Liang1, Rongdi Yin1, Lin Gui2, Jiachen Du1, Ruifeng Xu1 1Harbin Institute of Technology, Shenzhen, 2University of Warwick

METNet: A Mutual Enhanced Transformation Network for Aspect-based Sentiment Analysis Bin Jiang1, Jing Hou1, Wanyue Zhou1, Chao Yang1, Shihan Wang2, Liang Pang3 1Hunan University, 2Utrecht University, 3Chinese Academy of Sciences

Making the Best Use of Review Summary for Sentiment Analysis Sen Yang1, Leyang Cui2, Jun Xie3, Yue Zhang1 1Westlake University, 2Zhejiang University , Westlake University, 3Alibaba

From Sentiment Annotations to Sentiment Prediction through Discourse Augmentation Patrick Huber and Giuseppe Carenini University of British Columbia

End-to-End Emotion-Cause Pair Extraction with Graph Convolutional Network Ying Chen1, Wenjun Hou1, Shoushan Li2, Caicong Wu1, Xiaoqiang Zhang1 1China Agricultural University, 2Soochow University

A Unified Sequence Labeling Model for Emotion Cause Pair Extraction Xinhong Chen1, Qing Li2, Jianping Wang1 1City University of Hong Kong, 2the Hong Kong Polytechnic University

Regrexit or not Regrexit: Aspect-based Sentiment Analysis in Polarized Contexts Vorakit Vorakitphan1, Marco Guerini2, Elena Cabrio3, Serena Villata4 1Université Côte d’Azur, Inria, CNRS, I3S, France, 2Fondazione Bruno Kessler, 3Université Côte d’Azur, Inria, CNRS, I3S, 4Université Côte d’Azur, CNRS, Inria, I3S

Affective and Contextual Embedding for Sarcasm Detection Nastaran Babanejad1, Heidar Davoudi2, Aijun An3, Manos Papagelis3 1York University of Canada, 2Ontario Tech University, 3York University

Understanding Pre-trained BERT for Aspect-based Sentiment Analysis Hu Xu1, Lei Shu2, Philip Yu3, Bing Liu4 1Facebook, 2Amazon Alexa AI, 3Universtiy of Illinois at Chicago, 4University of Illinois at Chicago

Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis Minlong Peng and Qi Zhang Fudan University

Improving Sentiment Analysis over non-English Tweets using Multilingual Transformers and Automatic Translation for Data-Augmentation Valentin Barriere and Alexandra Balahur Joint Research Center

Joint Aspect Extraction and Sentiment Analysis with Directional Graph Convolutional Networks Guimin Chen1, Yuanhe Tian2, Yan Song3 1Shenzhen Research Institute of Big Data, 2Department of Linguistics, University of Washington, 3CUHK-SZ

16:00 - 16:30    Session IND1 - INDUSTRY TRACK: Dialogue - Room Gràcia Chair: Jianguo Zhang

Evaluating Cross-Lingual Transfer Learning Approaches in Multilingual Conversational Agent Models Lizhen Tan and Olga Golovneva

Data-Efficient Paraphrase Generation to Bootstrap Intent Classification and Slot Labeling for New Features in Task-Oriented Dialog Systems Shailza Jolly, Tobias Falke, Caglar Tirkaz and Daniil Sorokin

Leveraging User Paraphrasing Behavior In Dialog Systems To Automatically Collect Annotations For Long-Tail Utterances Tobias Falke, Markus Boese, Daniil Sorokin, Caglar Tirkaz and Patrick Lehnen

Query Distillation: BERT-based Distillation for Ensemble Ranking Wangshu Zhang, Junhong Liu, Zujie Wen, Yafang Wang and Gerard de Melo

Semantic Diversity for Natural Language Understanding Evaluation in Dialog Systems Enrico Palumbo, Andrea Mezzalira, Cristina Marco, Alessandro Manzotti and Daniele Amberti

16:00 - 16:30    Session ROADMAPS 1 - INDUSTRY ROADMAPS 1 (live) - Room Eixample Chair: Fei Yu Xu Co-Chair: Christian Reisswig

LUGE: An Open Source Project of Chinese NLP Datasets. Baidu Baidu

NLP at Lenovo Lenovo

Information extraction for cancer research and multi-modal language understanding/ generation at AIRC AIRC

Expert.AI: Natural Language Expertise for Explainable and Practical AI Expert AI

16:00 - 16:30    Session POSTER2 - Applications. Posters - Exhibition Room Vila Olímpica

Train Once, and Decode As You Like Chao Tian1, Yifei Wang2, Hao Cheng1, Yijiang Lian3, Zhihua Zhang2 1Academy for Advanced Interdisciplinary Studies, Peking University, 2School of Mathematical Sciences, Peking University, 3Baidu Inc.

A Representation Learning Approach to Animal Biodiversity Conservation Meet Mukadam, Mandhara Jayaram, Yongfeng Zhang Rutgers University

Integrating External Event Knowledge for Script Learning Shangwen Lv1, Fuqing Zhu1, Songlin Hu2 1Institute of Information Engineering, Chinese Academy of Sciences, 2Institute of Information Engineering, CAS

Pointing to Subwords for Generating Function Names in Source Code Shogo Fujita1, Hidetaka Kamigaito1, Hiroya Takamura2, Manabu Okumura1 1Tokyo institute of technology, 2The National Institute of Advanced Industrial Science and Technology (AIST)

Heterogeneous Graph Neural Networks to Predict What Happen Next Jianming Zheng, Fei Cai, Yanxiang Ling, Honghui Chen National University of Defense Technology

CEREC: A Corpus for Entity Resolution in Email Conversations Parag Pravin Dakle and Dan Moldovan The University of Texas at Dallas

SQL Generation via Machine Reading Comprehension ZEYU YAN1, Jianqiang Ma1, Yang Zhang2, Jianping Shen3 1Ping An Life, AI Department, 2AI Department, Pingan Life Insurance, 3Ping An Life

Towards Privacy by Design in Learner Corpora Research: A Case of On-the-fly Pseudonymization of Swedish Learner Essays Elena Volodina1, Yousuf Ali Mohammed1, Sandra Derbring1, Arild Matsson1, Beata Megyesi2 1University of Gothenburg, 2uu.se

PG-GSQL: Pointer-Generator Network with Guide Decoding for Cross-Domain Context-Dependent Text-to-SQL Generation Huajie Wang, Mei Li, Lei Chen East China Normal University

Neural Approaches for Natural Language Interfaces to Databases: A Survey Radu Cristian Alexandru Iacob1, Florin Brad2, Elena-Simona APOSTOL1, Ciprian-Octavian Truică1, Ionel Alexandru Hosu3, Traian Rebedea1 1University Politehnica of Bucharest, 2Bitdefender, 3Politehnica University of Bucharest

Predicting Stance Change Using Modular Architectures Aldo Porco and Dan Goldwasser Purdue University

Leveraging HTML in Free Text Web Named Entity Recognition Colin Ashby and David Weir University of Sussex

Multimodal Review Generation with Privacy and Fairness Awareness Xuan-Son Vu1, Thanh-Son Nguyen2, Duc-Trong Le3, Lili Jiang4 1PhD Student, 2A*STAR, 3UET, Vietnam National University in Hanoi, Vietnam, 4Department of Computing Science, Umeå University, Sweden

Generating Equation by Utilizing Operators : GEO model Kyung Seo Ki, Donggeon Lee, Bugeun Kim, Gahgene Gweon Seoul National University

16:30 - 17:00    Session LONG3 - Dialogue 1 - Room El Raval Chair: Wanxiang Che Co-Chair: Evan Jaffe

Improving Abstractive Dialogue Summarization with Graph Structures and Topic Words Lulu Zhao, Weiran Xu, Jun Guo Beijing University of Posts and Telecommunications

Speaker-change Aware CRF for Dialogue Act Classification Guokan Shang1, Antoine Tixier2, Michalis Vazirgiannis3, Jean-Pierre Lorré4 1École Polytechnique, 2Ecole Polytechnique, Palaiseau, France, 3Ecole Polytechnique, 4Linagora

LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimization Nurul Lubis1, Christian Geishauser2, Michael Heck1, Hsien-chin Lin1, Marco Moresi2, Carel van Niekerk1, Milica Gasic2 1Heinrich Heine University, 2Heinrich Heine University Duesseldorf

Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Survey Samuel Louvan1 and Bernardo Magnini2 1University of Trento - Fondazione Bruno Kessler, 2FBK

Re-framing Incremental Deep Language Models for Dialogue Processing with Multi-task Learning Morteza Rohanian and Julian Hough Queen Mary University of London

16:30 - 17:00    Session LONG4 - Information Extraction 2 - Room Montjuïc Chair: Carlos Ramisch Co-Chair: Danielly Sorato

AprilE: Attention with Pseudo Residual Connection for Knowledge Graph Embedding Yuzhang Liu1, Peng Wang1, Yingtai Li2, Yizhan Shao1, Zhongkai Xu1 1Southeast University, 2Southeast university, China

Variational Autoencoder with Embedded Student-t Mixture Model for Authorship Attribution Benedikt Boenninghoff1, Steffen Zeiler1, Robert Nickel2, Dorothea Kolossa1 1Ruhr-Universität Bochum, 2Bucknell University

Knowledge Graph Embeddings in Geometric Algebras Chengjin Xu1, Mojtaba Nayyeri1, Yung-Yu Chen1, Jens Lehmann2 1University of Bonn, 2University of Bonn and Fraunhofer IAIS

Exploiting Node Content for Multiview Graph Convolutional Network and Adversarial Regularization Qiuhao Lu1, Nisansa de Silva1, Dejing Dou1, Thien Huu Nguyen1, Prithviraj Sen2, Berthold Reinwald2, Yunyao Li3 1University of Oregon, 2IBM Research, 3IBM Research - Almaden

RatE: Relation-Adaptive Translating Embedding for Knowledge Graph Completion Hao Huang1, Guodong Long2, Tao Shen3, Jing Jiang3, Chengqi Zhang3 1Univerisity of Technology Sydney, 2UTS, 3University of Technology Sydney

16:30 - 17:00    Session LONG5 - Sentiment Analysis 1 - Room Gràcia Chair: Frank Xing Co-Chair: Zhaopeng Tu

SentiX: A Sentiment-Aware Pre-Trained Model for Cross-Domain Sentiment Analysis Jie Zhou1, Junfeng Tian2, Rui Wang2, Yuanbin Wu1, Wenming Xiao2, liang he1 1East China Normal University, 2Alibaba Group

Bayes-enhanced Lifelong Attention Networks for Sentiment Classification Hao Wang1, Shuai Wang2, Sahisnu Mazumder3, Bing Liu3, Yan Yang1, Tianrui Li1 1Southwest Jiaotong University, 2Amazon AI, 3University of Illinois at Chicago

Arabizi Language Models for Sentiment Analysis Gaétan Baert1, Souhir Gahbiche2, Guillaume Gadek3, Alexandre Pauchet4 1INSA Rouen Normandy - LITIS, 2AIRBUS, 3Normandie Univ, INSA Rouen, LITIS, 76000 Rouen, France ; Airbus DS, 4Normandy University - INSA Rouen Normandy - LITIS

Author’s Sentiment Prediction Mohaddeseh Bastan, Mahnaz Koupaee, Youngseo Son, Richard Sicoli, Niranjan Balasubramanian Stony Brook University

Modeling Local Contexts for Joint Dialogue Act Recognition and Sentiment Classification with Bi-channel Dynamic Convolutions Jingye Li, Hao Fei, Donghong Ji Wuhan University

16:30 - 17:00    Session POSTER3 - Applications: Biomedical, health records and medical texts. Posters - Exhibition Room Vila Olímpica

Named Entity Recognition for Chinese biomedical patents Yuting Hu and Suzan Verberne LIACS, Leiden University

Learning Health-Bots from Training Data that was Automatically Created using Paraphrase Detection and Expert Knowledge Anna Liednikova1, Philippe Jolivet2, Alexandre Durand-Salmon2, Claire Gardent3 1ALIAE and LORIA, 2ALIAE, 3CNRS/LORIA

A Joint Learning Approach based on Self-Distillation for Keyphrase Extraction from Scientific Documents Tuan Lai1, Trung Bui2, Doo Soon Kim2, Quan Hung Tran2 1University of Illinois at Urbana-Champaign, 2Adobe Research

Enhancing Clinical BERT Embedding using a Biomedical Knowledge Base Boran Hao1, Henghui Zhu2, Ioannis Paschalidis1 1Boston University, 2Amazon

TIMBERT: Toponym Identifier For The Medical Domain Based on BERT MohammadReza Davari, Leila Kosseim, Tien Bui Concordia University

BioMedBERT: A Pre-trained Biomedical Language Model for QA and IR SOURADIP CHAKRABORTY1, Ekaba Bisong2, Shweta Bhatt3, Thomas Wagner4, Riley Elliott4, Francesco Mosconi5 1Indian Statistical Institute, 2Carleton University, 3Jupiter, 4TPHS Research, 5Zero to Deep Learning

Extracting Adherence Information from Electronic Health Records Jordan Sanders1, Meghana Gudala2, Kathleen Hamilton1, Nishtha Prasad1, Jordan Stovall2, Eduardo Blanco1, Jane E Hamilton2, Kirk Roberts2 1University of North Texas, 2University of Texas Health Science Center at Houston

Identifying Depressive Symptoms from Tweets: Figurative Language Enabled Multitask Learning Framework Shweta Yadav1, Jainish Chauhan2, Joy Prakash Sain3, Krishnaprasad Thirunarayan3, Amit Sheth4, Jeremiah Schumm3 1National Library of Medicine, 2Indian Institute of Technology Gandhinagar, 3Wright State University, 4University of South Carolina

French Biomedical Text Simplification: When Small and Precise Helps Rémi Cardon1 and Natalia Grabar2 1CNRS UMR 8163 STL Université de Lille, 2CNRS STL UMR8163, Université de Lille

Summarizing Medical Conversations via Identifying Important Utterances Yan Song1, Yuanhe Tian2, Nan Wang3, Fei Xia4 1CUHK-SZ, 2Department of Linguistics, University of Washington, 3Hunan University, 4University of Washington

17:00 - 17:30    Session LONG6 - Language Modelling 2 - Room El Raval Chair: Sebastian Ruder Co-Chair: Harish Tayyar Madabushi

Probing Multimodal Embeddings for Linguistic Properties: the Visual-Semantic Case Adam Dahlgren Lindström, Johanna Björklund, Suna Bensch, Frank Drewes Umeå University

Linguistic Profiling of a Neural Language Model Alessio Miaschi1, Dominique Brunato2, Felice Dell'Orletta3, Giulia Venturi4 1University of Pisa, 2Institute of Computational Linguistics "A. Zampolli" (ILC-CNR), Pisa, 3ItaliaNLP LAb @ Institute for Computational Linguistics "Antonio Zampolli", ILC - CNR, 4Institute of Computational Linguistics "Antonio Zampolli" (ILC-CNR)

IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP Fajri Koto1, Afshin Rahimi2, Jey Han Lau1, Timothy Baldwin1 1The University of Melbourne, 2The University of Queensland

A Closer Look at Linguistic Knowledge in Masked Language Models: The Case of Relative Clauses in American English Marius Mosbach, Stefania Degaetano-Ortlieb, Marie-Pauline Krielke, Badr M. Abdullah, Dietrich Klakow Saarland University

Modeling language evolution and feature dynamics in a realistic geographic environment Rhea Kapur1 and Phillip Rogers2 1The Pingry School, 2University of California Santa Barbara

17:00 - 17:30    Session LONG7 - Sentiment Analysis 2 - Room Montjuïc Chair: Rui Xia Co-Chair: Yufang Hou

Syntax-Aware Graph Attention Network for Aspect-Level Sentiment Classification Lianzhe Huang1, Xin Sun1, Sujian Li2, Linhao Zhang1, Houfeng Wang1 1Peking University, 2pku.edu.cn

Attention Transfer Network for Aspect-level Sentiment Classification Fei Zhao1, Zhen Wu1, Xinyu Dai2 1Nanjing University, 2National Key Laboratory for Novel Software Technology, Nanjing University

Label Correction Model for Aspect-based Sentiment Analysis Qianlong Wang and Jiangtao Ren Sun Yat-sen University

Aspect-Category based Sentiment Analysis with Hierarchical Graph Convolutional Network Hongjie Cai1, Yaofeng Tu2, Xiangsheng Zhou2, Jianfei Yu1, Rui Xia1 1Nanjing University of Science and Technology, 2ZTE Corporation, Shenzhen, China

Constituency Lattice Encoding for Aspect Term Extraction Yunyi Yang1, Kun Li1, Xiaojun Quan1, Weizhou Shen1, Qinliang Su2 1School of Data and Computer Science, Sun Yat-sen University, 2Sun Yat-sen University

17:00 - 17:30    Session LONG8 - Applications1 - Room Gràcia Chair: Miryam de Lhoneux

A Corpus for Argumentative Writing Support in German Thiemo Wambsganss1, Christina Niklaus2, Matthias Söllner3, Siegfried Handschuh2, Jan Marco Leimeister4 1University of St.Gallen, 2University of St. Gallen, 3University of Kassel, 4University of St.Gallen & University of Kassel

Do Word Embeddings Capture Spelling Variation? Dong Nguyen1 and Jack Grieve2 1Utrecht University, 2University of Birmingham

Don’t take “nswvtnvakgxpm” for an answer –The surprising vulnerability of automatic content scoring systems to adversarial input Yuning Ding1, Brian Riordan2, Andrea Horbach3, Aoife Cahill4, Torsten Zesch5 1University Duisburg Essen, 2ETS, 3University of Duisburg-Essen, 4Educational Testing Service, 5Language Technology Lab, University of Duisburg-Essen

Automated Prediction of Examinee Proficiency from Short-Answer Questions Le An Ha1, Victoria Yaneva2, Polina Harik3, Ravi Pandian3, Amy Morales3, Brian Clauser3 1RGCL, RIILP, University of Wolverhampton, 2University of Wolverhampton; National Board of Medical Examiners, 3National Board of Medical Examiners

Exploring Cross-sentence Contexts for Named Entity Recognition with BERT Jouni Luoma and Sampo Pyysalo University of Turku

17:00 - 17:30    Session POSTER4 - Applications: Legal, financial, business, humanities. Posters - Exhibition Room Vila Olímpica

Cross-lingual Annotation Projection in Legal Texts Andrea Galassi1, Kasper Drazewski2, Marco Lippi3, Paolo Torroni4 1University of Bologna, 2Bureau Européen des Unions de Consommateurs, 3University of Modena and Reggio Emilia, 4Alma Mater - Università di Bologna

Deep Learning Framework for Measuring the Digital Strategy of Companies from Earnings Calls Ahmed Ghanim Al-Ali1, Robert Phaal1, Donald Sull2 1Department of Engineering, University of Cambridge, 2MIT Sloan School of Management

A Dataset and Evaluation Framework for Complex Geographical Description Parsing Egoitz Laparra and Steven Bethard University of Arizona

DocBank: A Benchmark Dataset for Document Layout Analysis Minghao Li1, Yiheng Xu2, Lei Cui2, Shaohan Huang2, Furu Wei3, Zhoujun Li1, Ming Zhou2 1Beihang University, 2Microsoft Research Asia, 3Microsoft Research

Building Large-Scale English and Korean Datasets for Aspect-Level Sentiment Analysis in Automotive Domain Dongmin Hyun, Junsu Cho, Hwanjo Yu Pohang University of Science and Technology (POSTECH)

A High Precision Pipeline for Financial Knowledge Graph Construction Sarah Elhammadi1, Laks V.S. Lakshmanan1, Raymond Ng1, Michael Simpson1, Baoxing Huai2, Zhefeng Wang2, Lanjun Wang2 1University of British Columbia, 2Huawei

Financial Sentiment Analysis: An Investigation into Common Mistakes and Silver Bullets Frank Xing1, Lorenzo Malandri2, Yue Zhang3, Erik Cambria1 1Nanyang Technological University, 2University of Milan - Bicocca, 3Westlake University

Answering Legal Questions by Learning Neural Attentive Text Representation Phi Manh Kien1, Ha-Thanh Nguyen2, Ngo Xuan Bach1, Vu Tran2, Minh Le Nguyen2, Tu Minh Phuong1 1Department of Computer Science, Posts and Telecommunications Institute of Technology, Hanoi, Vietnam, 2Japan Advanced Institute of Science and Technology

Joint Transformer/RNN Architecture for Gesture Typing in Indic Languages Emil Biju1, Anirudh Sriram1, Mitesh M. Khapra1, Pratyush Kumar2 1Indian Institute of Technology Madras, 2IIT Madras

Automatic Charge Identification from Facts: A Few Sentence-Level Charge Annotations is All You Need Shounak Paul1, Pawan Goyal2, Saptarshi Ghosh2 1Indian Institute of Technology, Kharagpur, 2IIT Kharagpur

Context-Aware Text Normalisation for Historical Dialects Maria Sukhareva Goethe University Frankfurt

RuSemShift: a dataset of historical lexical semantic change in Russian Julia Rodina1 and Andrey Kutuzov2 1National Research University Higher School of Economics, 2University of Oslo

Exploring Amharic Sentiment Analysis from Social Media Texts: Building Annotation Tools and Classification Models Seid Muhie Yimam1, Hizkiel Mitiku Alemayehu2, Abinew Ayele3, Chris Biemann1 1Universität Hamburg, 2Università di Bologna, 3University of Hamburg, Bahir Dar University

Effective Few-Shot Classification with Transfer Learning Aakriti Gupta1, Kapil Thadani2, Neil O'Hare2 1Verizon Media, 2Yahoo Research

17:30 - 18:00    Session LONG9 - Multimodal 1 - Room El Raval Chair: Iacer Calixto Co-Chair: Orphee Declerq

SWAFN: Sentimental Words Aware Fusion Network for Multimodal Sentiment Analysis Minping Chen and Xia Li Guangdong University of Foreign Studies

Multimodal Topic-Enriched Auxiliary Learning for Depression Detection Minghui An, Jingjing Wang, Shoushan Li, Guodong Zhou Soochow University

Imagining Grounded Conceptual Representations from Perceptual Information in Situated Guessing Games Alessandro Suglia1, Antonio Vergari2, Ioannis Konstas1, Yonatan Bisk3, Emanuele Bastianelli1, Andrea Vanzo1, Oliver Lemon1 1Heriot-Watt University, 2University of California, Los Angeles, 3Carnegie Mellon University

Situated and Interactive Multimodal Conversations Seungwhan Moon1, Satwik Kottur2, Paul Crook3, Ankita De3, Shivani Poddar2, Theodore Levin4, David Whitney3, Daniel Difranco3, Ahmad Beirami3, Eunjoon Cho3, Rajen Subba3, Alborz Geramifard5 1Facebook Conversational AI, 2Carnegie Mellon University, 3Facebook, 4Facebook Asssistant, 5Facebook AI

Meet Changes with Constancy: Learning Invariance in Multi-Source Translation Jianfeng Liu1, Ling Luo2, Xiang Ao3, Yan Song4, Haoran Xu1, Jian Ye1 1Institute of Computing Technology of the Chinese Academy of Sciences, 2Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China, 3Institute of Computing Technology, Chinese Academy of Sciences, 4CUHK-SZ

17:30 - 18:00    Session LONG10 - Machine learning 1 - Room Montjuïc Chair: Jong C. Park Co-Chair: Jacopo Tagliabue

Enhancing Neural Models with Vulnerability via Adversarial Attack Rong Zhang1, Qifei Zhou1, Bo An2, Weiping Li1, Tong Mo1, Bo Wu3 1Peking University, 2Institute of Software, Chinese Academy of Sciences, 3MIT-IBM Watson AI Lab

R-VGAE: Relational-variational Graph Autoencoder for Unsupervised Prerequisite Chain Learning Irene Li1, Alexander Fabbri1, Swapnil Hingmire2, Dragomir Radev1 1Yale University, 2TRDDC, TCS Research And Innovation

Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning Daniel Grießhaber1, Johannes Maucher1, Ngoc Thang Vu2 1Hochschule der Medien, 2University of Stuttgart

Exploring End-to-End Differentiable Natural Logic Modeling Yufei Feng1, Zi'ou Zheng1, Quan Liu2, Michael Greenspan1, Xiaodan Zhu1 1Queen's University, 2National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China; State Key Laboratory of Cognitive Intelligence, iFLYTEK Research, Hefei, China

A Semantically Consistent and Syntactically Variational Encoder-Decoder Framework for Paraphrase Generation Wenqing Chen1, Jidong Tian2, Liqiang Xiao3, Hao He4, Yaohui Jin4 1State Key Lab of Advanced Optical Communication System and Network, Shanghai Jiao Tong University;Artificial Intelligence Institute, Shanghai Jiao Tong University, 2State Key Lab of Advanced Optical Communication System and Network, Shanghai Jiao Tong University; Artificial Intelligence Institute, Shanghai Jiao Tong University, 3Artificial Intelligence Institute, Shanghai Jiao Tong University, 4Shanghai Jiao Tong University

17:30 - 18:00    Session POSTER5 - Semantics 1. Posters - Exhibition Room Vila Olímpica

Tiny Word Embeddings Using Globally Informed Reconstruction Sora Ohashi1, Mao Isogawa1, Tomoyuki Kajiwara2, Yuki Arase2 1Graduate School of Information Science and Technology, Osaka University, 2Osaka University

Improving Word Embeddings through Iterative Refinement of Word- and Character-level Models Phong Ha1, Shanshan Zhang1, Nemanja Djuric2, Slobodan Vucetic1 1Temple University, 2Uber ATG

Probing Multilingual BERT for Genetic and Typological Signals Taraka Rama1, Lisa Beinborn2, Steffen Eger3 1University of North Texas at Denton, 2Vrije Universiteit Amsterdam, 3NLLG Lab, Technische Universität Darmstadt

Learning Efficient Task-Specific Meta-Embeddings with Word Prisms Jingyi He1, KC Tsiolis1, Kian Kenyon-Dean2, Jackie Chi Kit Cheung2 1Mila, McGill University, 2McGill University

Always Keep your Target in Mind: Studying Semantics and Improving Performance of Neural Lexical Substitution Nikolay Arefyev1, Boris Sheludko2, Alexander Podolskiy3, Alexander Panchenko4 1Lomonosov Moscow State University, Samsung R&D Institute, National Research University Higher School of Economics, Russia, 2Samsung R&D Institute Russia, Lomonosov Moscow State University, 3Samsung Research Russia, 4Skolkovo Institue of Science and Technology

Word Embedding Binarization with Semantic Information Preservation Samarth Navali, Praneet Sherki, Ramesh Inturi, Vanraj Vala Samsung Research, Bangalore

How Relevant Are Selectional Preferences for Transformer-based Language Models? Eleni Metheniti1, Tim Van de Cruys2, Nabil Hathout3 1CLLE-CNRS and IRIT-CNRS, 2University of Leuven, 3CLLE/ERSS, CNRS & Université de Toulouse

Embedding Semantic Taxonomies Alyssa Lees1, Chris Welty2, Shubin Zhao3, Jacek Korycki1, Sara Mc Carthy1 1Google, 2NA, 3Google Research

A Retrofitting Model for Incorporating Semantic Relations into Word Embeddings Sapan Shah1, Sreedhar Reddy1, Pushpak Bhattacharyya2 1Tata Consultancy Services Ltd, 2Indian Institute of Technology Bombay and Patna

Lexical Relation Mining in Neural Word Embeddings Aishwarya Jadhav1, Yifat Amir2, Zachary Pardos3 1Carnegie Mellon University, 2Google, 3UC Berkeley

A BERT-based Dual Embedding Model for Chinese Idiom Prediction Minghuan Tan and Jing Jiang Singapore Management University

BERT-based Cohesion Analysis of Japanese Texts Nobuhiro Ueda1, Daisuke Kawahara2, Sadao Kurohashi1 1Kyoto University, 2Waseda University

Schema Aware Semantic Reasoning for Interpreting Natural Language Queries in Enterprise Settings Jaydeep Sen1, Tanaya Babtiwale2, Kanishk Saxena3, Yash Butala4, Sumit Bhatia1, Karthik Sankaranarayanan1 1IBM Research AI, 2NMIMS University, 3Sir M. Visvesvaraya Institute of Technology, 4Indian Institute of Technology Kharagpur

18:00 - 18:30    Session LONG11 - Semantics 1 - Room El Raval Chair: Jose Camacho-Collados Co-Chair: Guy Emerson

Multilingual Irony Detection with Dependency Syntax and Neural Models Alessandra Teresa Cignarella1, Valerio Basile2, Manuela Sanguinetti3, Cristina Bosco4, Paolo Rosso5, Farah Benamara6 1Dipartimento di Informatica - Università degli studi di Torino, 2University of Turin, 3University of Cagliari, Department of Mathematics and Computer Science, 4Dipartimento di Informatica - Università di Torino, 5Universitat Politècnica de València, 6University of toulouse

What Can We Learn from Noun Substitutions in Revision Histories? Talita Anthonio and Michael Roth University of Stuttgart

Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity Anne Lauscher1, Ivan Vulić2, Edoardo Maria Ponti3, Anna Korhonen2, Goran Glavaš1 1University of Mannheim, 2University of Cambridge, 3Mila Montreal / University of Cambridge

Harnessing Cross-lingual Features to Improve Cognate Detection for Low-resource Languages Diptesh Kanojia1, Raj Dabre2, Shubham Dewangan3, Pushpak Bhattacharyya4, Gholamreza Haffari5, Malhar Kulkarni6 1IITB-Monash Research Academy, 2NICT, 3IIT Bombay, 4Indian Institute of Technology Bombay and Patna, 5Monash University, 6IIT Bombay, India

Bridging the Gap in Multilingual Semantic Role Labeling: a Language-Agnostic Approach Simone Conia and Roberto Navigli Sapienza University of Rome

18:00 - 18:30    Session LONG12 - Simplification - Room Gràcia Chair: Carolina Scarton

On the Helpfulness of Document Context to Sentence Simplification Renliang Sun, Zhe Lin, Xiaojun Wan Peking University

AutoMeTS: The Autocomplete for Medical Text Simplification Hoang Van1, David Kauchak2, Gondy Leroy1 1University of Arizona, 2Pomona College

Multi-Word Lexical Simplification Piotr Przybyła1 and Matthew Shardlow2 1Institute of Computer Science, Polish Academy of Sciences, 2Manchester Metropolitan University

18:00 - 18:30    Session SHORT1 - Machine Learning methods. Short papers - Room Montjuïc Chair: Jinhua Du

Exploring the zero-shot limit of FewRel alberto cetoli QBE

A Deep Generative Distance-Based Classifier for Out-of-Domain Detection with Mahalanobis Space Hong Xu, Keqing He, Yuanmeng Yan, Sihong Liu, Zijun Liu, Weiran XU Beijing University of Posts and Telecommunications

Contrastive Zero-Shot Learning for Cross-Domain Slot Filling with Adversarial Attack Keqing He1, Jinchao Zhang2, Yuanmeng Yan1, Weiran XU1, Cheng Niu3, Jie Zhou4 1Beijing University of Posts and Telecommunications, 2Pattern Recognition Center, WeChat AI, Tencent, 3Tencent America, 4Tencent Inc.

DoLFIn: Distributions over Latent Features for Interpretability Phong Le1 and Willem Zuidema2 1Amazon, 2University of Amsterdam

Contextual Argument Component Classification for Class Discussions Luca Lugini and Diane Litman University of Pittsburgh

On the Practical Ability of Recurrent Neural Networks to Recognize Hierarchical Languages Satwik Bhattamishra1, Kabir Ahuja2, Navin Goyal3 1Microsoft Research India, 2Microsoft Research, 3Microsoft

Pre-trained Language Model Based Active Learning for Sentence Matching Guirong Bai1, Shizhu He1, Kang Liu1, Jun Zhao2, Zaiqing Nie3 1Institute of Automation, Chinese Academy of Sciences, 2Chinese Academy of Sciences, 3Alibaba

Event-Guided Denoising for Multilingual Relation Learning Amith Ananthram1, Emily Allaway1, Kathleen McKeown2 1Columbia University, 2Columbia University and Amazon (Amazon Scholar)

Using a Penalty-based Loss Re-estimation Method to Improve Implicit Discourse Relation Classification xiao li1, Yu Hong1, Huibin Ruan1, Zhen Huang2 1Soochow University, 2National University of Defense Technology

18:00 - 18:30    Session POSTER6 - Information Extraction and Knowledge Graphs. Posters - Exhibition Room Vila Olímpica

A Review of Dataset and Labeling Methods for Causality Extraction Jinghang Xu, Wanli Zuo, Shining Liang, Xianglin Zuo Jilin University

Knowledge Graph Embedding with Atrous Convolution and Residual Learning Feiliang Ren, Juchen Li, Huihui Zhang, Shilei Liu, Bochao Li, Ruicheng Ming, Yujia Bai Northerstern University

KnowDis: Knowledge Enhanced Data Augmentation for Event Causality Detection via Distant Supervision Xinyu Zuo1, Yubo Chen1, Kang Liu1, Jun Zhao2 1Institute of automation, Chinese academy of sciences, 2Chinese Academy of Sciences

Graph Enhanced Dual Attention Network for Document-Level Relation Extraction Bo Li, Wei Ye, Zhonghao Sheng, Rui Xie, Xiangyu Xi, Shikun Zhang Peking University

Joint Entity and Relation Extraction for Legal Documents with Legal Feature Enhancement Yanguang Chen1, Yuanyuan Sun1, Zhihao Yang2, Hongfei LIN1 1Dalian University of Technology, 2Dalian University of Technogy

TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking Yucheng Wang1, Bowen Yu1, Yueyang Zhang2, Tingwen Liu1, Hongsong Zhu1, Limin Sun1 1Institute of Information Engineering, Chinese Academy of Sciences, 2Baidu, Inc

TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation Chengjin Xu1, Mojtaba Nayyeri1, Fouad Alkhoury2, Hamed Shariat Yazdi1, Jens Lehmann3 1University of Bonn, 2Uni Bonn, 3University of Bonn and Fraunhofer IAIS

Meta-Information Guided Meta-Learning for Few-Shot Relation Classification Bowen Dong1, Yuan Yao1, Ruobing Xie2, Tianyu Gao3, Xu Han1, Zhiyuan Liu1, Fen Lin2, Leyu Lin2, Maosong Sun1 1Tsinghua University, 2WeChat Search Application Department, Tencent, China, 3Princeton University

Unsupervised Deep Language and Dialect Identification for Short Texts Koustava Goswami1, Rajdeep Sarkar2, Bharathi Raja Chakravarthi1, Theodorus Fransen3, John P. McCrae4 1Insight Centre for Data Analytics, Data Science Institute, National University of Ireland Galway, 2Data Science Institute, NUI Galway, 3Insight Centre for Data Analytics, National University of Ireland, Galway, 4Insight Center for Data Analytics, National University of Ireland Galway

A Two-phase Prototypical Network Model for Incremental Few-shot Relation Classification Haopeng Ren1, Yi Cai1, Xiaofeng Chen1, Guohua Wang1, Qing Li2 1South China University of Technology, 2the Hong Kong Polytechnic University

Document-level Relation Extraction with Dual-tier Heterogeneous Graph Zhenyu Zhang1, Bowen Yu1, Xiaobo Shu1, Tingwen Liu1, Hengzhu Tang1, Wang Yubin2, Li Guo1 1Institute of Information Engineering, Chinese Academy of Sciences, 2Institute of Information Engineering，Chinese Academy of Sciences

Biased TextRank: Unsupervised Graph-Based Content Extraction Ashkan Kazemi, Verónica Pérez-Rosas, Rada Mihalcea University of Michigan

Improving Long-Tail Relation Extraction with Collaborating Relation-Augmented Attention Yang Li1, Tao Shen1, Guodong Long2, Jing Jiang1, Tianyi Zhou3, Chengqi Zhang1 1University of Technology Sydney, 2UTS, 3University of Washington

ToHRE: A Top-Down Classification Strategy with Hierarchical Bag Representation for Distantly Supervised Relation Extraction Erxin Yu1, Wenjuan Han2, Yuan Tian1, Yi Chang3 1Jilin university, 2National University of Singapore, 3School of Artificial Intelligence, Jilin University

Improving Relation Extraction with Relational Paraphrase Sentences Junjie Yu1, Tong Zhu1, Wenliang Chen1, Wei Zhang2, Min Zhang3 1Soochow University, 2Alibaba Group, 3Suda

18:30 - 19:00    Session SHORT2 - Semantics. Short Papers - Room Montjuïc Chair: Aline Villavicencio Co-Chair: Thiemo Wambsganss

Autoencoding Improves Pre-trained Word Embeddings Masahiro Kaneko1 and Danushka Bollegala2 1Tokyo Metropolitan University, 2University of Liverpool/Amazon

PoD: Positional Dependency-Based Word Embedding for Aspect Term Extraction Yichun Yin1, Chenguang Wang2, Ming Zhang3 1Huawei Noah’s Ark Lab, 2Amazon Web Services, 3Peking University

Unequal Representations: Analyzing Intersectional Biases in Word Embeddings Using Representational Similarity Analysis Michael Lepori Johns Hopkins University

Vec2Sent: Probing Sentence Embeddings with Natural Language Generation Martin Kerscher1 and Steffen Eger2 1Department of Computer Science, Technische Universität Darmstadt, 2NLLG Lab, Technische Universität Darmstadt

Multi-Task Learning for Knowledge Graph Completion with Pre-trained Language Models Bosung Kim1, Taesuk Hong2, Youngjoong Ko1, Jungyun Seo2 1Sungkyunkwan University, 2Sogang University

comp-syn: Perceptually Grounded Word Embeddings with Color Bhargav Srinivasa Desikan1, Tasker Hull2, Ethan Nadler3, Douglas Guilbeault4, Aabir Abubakar Kar1, Mark Chu5, Donald Ruggiero Lo Sardo6 1University of Chicago, 2Psiphon Inc, Toronto, 3Stanford University, 4University of California Berkeley, 5Columbia University, 6Medical University of Vienna

Try to Substitute: An Unsupervised Chinese Word Sense Disambiguation Method Based on HowNet Bairu Hou1, Fanchao Qi2, Yuan Zang3, Xurui Zhang3, Zhiyuan Liu4, Maosong Sun4 1School of Economic and Management, Tsinghua University, 2Tsinghua Univeristy, 3Department of Computer Science and Technology, Tsinghua University, 4Tsinghua University

Combining Event Semantics and Degree Semantics for Natural Language Inference Izumi Haruta1, Koji Mineshima2, Daisuke Bekki1 1Ochanomizu University, 2Keio University

18:30 - 19:00    Session SHORT3 - Applications. Short papers - Room El Raval Chair: Mariona Coll Co-Chair: Matthias Aßenmacher

Complaint Identification in Social Media with Transformer Networks Mali Jin and Nikolaos Aletras University of Sheffield

Syntactically Aware Cross-Domain Aspect and Opinion Terms Extraction Oren Pereg1, Daniel Korat2, Moshe Wasserblat2 1AI Lab, Intel Labs, 2Intel AI Lab

A Deep Generative Approach to Native Language Identification Ehsan Lotfi, Ilia Markov, Walter Daelemans University of Antwerp, CLiPS

Modeling Event Salience in Narratives via Barthes’ Cardinal Functions Takaki Otake1, Sho Yokoi2, Naoya Inoue3, Ryo Takahashi1, Tatsuki Kuribayashi4, Kentaro Inui5 1Tohoku University, 2Tohoku University / RIKEN AIP, 3Stony Brook University, 4Tohoku University / Langsmith Inc., 5Tohoku University / Riken

Medical Knowledge-enriched Textual Entailment Framework Shweta Yadav1, Vishal Pallagani2, Amit Sheth2 1National Library of Medicine, 2University of South Carolina, USA

Predicting Personal Opinion on Future Events with Fingerprints Fan Yang1, Eduard Dragut2, Arjun Mukherjee1 1University of Houston, 2Temple University

Detecting de minimis Code-Switching in Historical German Books Shijia Liu and David Smith Northeastern University

Lin: Unsupervised Extraction of Tasks from Textual Communication Parth Diwanji1, Hui Guo1, Munindar Singh1, Anup Kalia2 1North Carolina State University, 2IBM T. J. Watson Research Center

Connecting the Dots Between Fact Verification and Fake News Detection Qifei LI and Wangchunshu Zhou Beihang University

18:30 - 19:00    Session POSTER7 - Multimodality. Posters - Exhibition Room Vila Olímpica

Personalized Multimodal Feedback Generation in Education Haochen Liu1, Zitao Liu2, Zhongqin Wu2, Jiliang Tang1 1Michigan State University, 2TAL Education Group

Reasoning Step-by-Step: Temporal Sentence Localization in Videos via Deep Rectification-Modulation Network Daizong Liu1, Xiaoye Qu1, Jianfeng Dong2, Pan Zhou1 1Huazhong University of Science and Technology, 2Zhejiang Gongshang University

RIVA: A Pre-trained Tweet Multimodal Model Based on Text-image Relation for Multimodal NER Lin Sun1, Jiquan Wang2, Yindu Su2, Fangsheng Weng1, Yuxuan Sun1, Zengwei Zheng1, Yuanyi Chen1 1Zhejiang University City College, 2Zhejiang University

Towards Knowledge-Augmented Visual Question Answering Maryam Ziaeefard1 and Freddy Lecue2 1Thales Digital Solutions, 2Inria

Visual-Textual Alignment for Graph Inference in Visual Dialog Tianling Jiang, Yi Ji, Chunping Liu, Hailin Shao Soochow University

Ad Lingua: Text Classification Improves Symbolism Prediction in Image Advertisements Andrey Savchenko1, Anton Alekseev2, Sejeong Kwon3, Elena Tutubalina4, Evgeny Myasnikov1, Sergey Nikolenko5 1Samsung-PDMI Joint AI Center, Steklov Mathematical Institute at St. Petersburg, 2St. Petersburg Department of Steklov Mathematical Institute of Russian Academy of Sciences, 3Samsung Research, 4Kazan Federal University, 5Steklov Math. Institute

Humans Meet Models on Object Naming: A New Dataset and Analysis Carina Silberer1, Sina Zarrieß2, Matthijs Westera3, Gemma Boleda4 1University of Stuttgart, 2University of Jena, 3Universitat Pompeu Fabra, 4Universitat Pompeu Fabra / ICREA

Encoding Lexico-Semantic Knowledge using Ensembles of Feature Maps from Deep Convolutional Neural Networks Steven Derby1, Paul Miller1, Barry Devereux2 1Queen's University Belfast, 2Queen's University, Belfast

Language-Driven Region Pointer Advancement for Controllable Image Captioning Annika Lindh, Robert Ross, John Kelleher Technological University Dublin

Offensive Language Detection on Video Live Streaming Chat Zhiwei Gao, Shuntaro Yada, Shoko Wakamiya, Eiji Aramaki Nara Institute of Science and Technology

Image Caption Generation for News Articles Zhishen Yang and Naoaki Okazaki Tokyo Institute of Technology

CoNAN: A Complementary Neighboring-based Attention Network for Referring Expression Generation Jungjun Kim1, Hanbin Ko1, Jialin Wu2 1Korea University, 2University of Texas at Austin

19:00 - 20:30    Big reception on gather.town

19:00 - 19:30    Session SOCIAL1 - Queer in AI Social Event

Wednesday, December 9, 2020

14:30 - 15:00    Session SOCIAL2 - Bon profit! Catalan cooking class with COLING'2020 organizers

Chef: Joan Gurgui; Cooking Assistants: Laura Pérez Mayos & Horacio Saggion (COLING organization team) Filmed and edited by Tulio Goncalves Menu (donwload recipes): Starters: Timbal d’escalivada amb formatge de cabra / Escalivada with goat cheese Main: Mandonguilles mar i muntanya / Sea and Mountain Meatballs Dessert: Panellets

15:00 - 15:30    INVITED TALK 2 - Room Poblenou Chair: Roberto Navigli

The computational linguistics of conversation modeling Amanda Stent NLP Architect at Bloomberg LP

15:30 - 16:00    Session LONG13 - Language Generation 1 - Room Monjtuic Chair: Simon Mille

Mark-Evaluate: Assessing Language Generation using Population Estimation Methods Gonçalo Mordido and Christoph Meinel Hasso Plattner Institute

TableGPT: Few-shot Table-to-Text Generation with Table Structure Reconstruction and Content Matching Heng Gong1, Yawei Sun1, Xiaocheng Feng2, Bing Qin1, Wei Bi3, Xiaojiang Liu3, Ting Liu1 1Harbin Institute of Technology, 2Harbin Institute of Technology,SCIR lab, 3Tencent AI Lab

The ApposCorpus: a new multilingual, multi-domain dataset for factual appositive generation Yova Kementchedjhieva1, Di Lu2, Joel Tetreault2 1University of Copenhagen, 2Dataminr

Generalized Shortest-Paths Encoders for AMR-to-Text Generation Lisa Jin and Daniel Gildea University of Rochester

An Enhanced Knowledge Injection Model for Commonsense Generation Zhihao Fan1, Yeyun Gong2, Zhongyu Wei3, Siyuan Wang1, Yameng Huang4, Jian Jiao4, Xuanjing Huang1, Nan Duan2, Ruofei Zhang4 1Fudan University, 2Microsoft Research Asia, 3School of Data Science, Fudan University, 4Microsoft

15:30 - 16:00    Session LONG14 - Parsing and Segmentation - Room El Raval Chair: Luis Espinosa-Anke Co-Chair: Ling Liu

Multi-grained Chinese Word Segmentation with Weakly Labeled Data Chen Gong1, Zhenghua Li1, Bowei Zou2, Min Zhang3 1Soochow University, 2Institute for Infocomm Research, ASTAR, 3Suda

KeyGames: A Game Theoretic Approach to Automatic Keyphrase Extraction Arnav Saxena, Mudit Mangal, Goonjan Jain Delhi Technological University

Parsers Know Best: German PP Attachment Revisited Bich-Ngoc Do1 and Ines Rehbein2 1Heidelberg University, 2University of Mannheim

Session LONG14 - Towards Fast and Accurate Neural Chinese Word Segmentation with Multi-Criteria Learning Weipeng Huang1, Xingyi Cheng2, Kunlong Chen3, Taifeng Wang4, Wei Chu1 1Ant Financial, 2Ant Financial Services Group, 3Ant Financial Service, 4Ant Finance

Joint Chinese Word Segmentation and Part-of-speech Tagging via Multi-channel Attention of Character N-grams Yuanhe Tian1, Yan Song2, Fei Xia3 1Department of Linguistics, University of Washington, 2CUHK-SZ, 3University of Washington

15:30 - 16:00    Session POSTER8 - Applications: grammar correction, support for language and script writing. Posters - Exhibition Room Vila Olímpica

Taking the Correction Difficulty into Account in Grammatical Error Correction Evaluation Takumi Gotou1, Ryo Nagata2, Masato Mita3, Kazuaki Hanawa3 1Konan Univercity, 2Konan University, 3RIKEN AIP / Tohoku University

Automatic Distractor Generation for Multiple Choice Questions in Standard Tests Zhaopeng Qiu1, Xian Wu2, Wei Fan1 1Tencent Medical AI Lab, 2Tencent

Towards A Friendly Online Community: An Unsupervised Style Transfer Framework for Profanity Redaction Minh Tran1, Yipeng Zhang2, Mohammad Soleymani1 1University of Southern California, 2University of Rochester

How Positive Are You: Text Style Transfer using Adaptive Style Embedding Heejin Kim and Kyung-Ah Sohn Ajou University

Neural text normalization leveraging similarities of strings and sounds Riku Kawamura1, Tatsuya Aoki1, Hidetaka Kamigaito1, Hiroya Takamura2, Manabu Okumura1 1Tokyo Institute of Technology, 2The National Institute of Advanced Industrial Science and Technology (AIST)

Generating Diverse Corrections with Local Beam Search for Grammatical Error Correction Kengo Hotate, Masahiro Kaneko, Mamoru Komachi Tokyo Metropolitan University

A Neural Local Coherence Analysis Model for Clarity Text Scoring Panitan Muangkammuen1, Sheng Xu2, Fumiyo Fukumoto1, Kanda Runapongsa Saikaew3, Jiyi Li1 1University of Yamanashi, 2Hangzhou Dianzi University, 3Khon Kaen University

Grammatical error detection in transcriptions of spoken English Andrew Caines1, Christian Bentz2, Kate Knill1, Marek Rei3, Paula Buttery1 1University of Cambridge, 2University of Tübingen, 3Imperial College London

Automatic Assistance for Academic Word Usage Dariush Saberi1, John Lee1, Jonathan James Webster2 1City University of Hong Kong, 2The Halliday Centre for Intelligent Applications of Language Studies

Style versus Content: A distinction without a (learnable) difference? Somayeh Jafaritazehjani1, Gwénolé Lecorvé2, Damien Lolive2, John Kelleher3 1Technological University Dublin, 2Univ Rennes, CNRS, IRISA, 3Technological University Dublin

Contextualized Embeddings for Enriching Linguistic Analyses on Politeness Ahmad Aljanaideh, Eric Fosler-Lussier, Marie-Catherine de Marneffe The Ohio State University

Heterogeneous Recycle Generation for Chinese Grammatical Error Correction Charles Hinson1, Hen-Hsen Huang2, Hsin-Hsi Chen1 1National Taiwan University, 2Department of Computer Science, National Chengchi University

Improving Grammatical Error Correction with Data Augmentation by Editing Latent Representation Zhaohong Wan1, Xiaojun Wan1, Wenguang Wang2 1Peking University, 2DataGrand Tech Inc.

16:00 - 16:30    Session IND2 - INDUSTRY TRACK - Generation and Question Answering - Room Gràcia Chair: Daniele Bonadiman

An Empirical Study on Multi-Task Learning for Text Style Transfer and Paraphrase Generation Pawel Bujnowski, Kseniia Ryzhova, Hyungtak Choi, Katarzyna Witkowska, Jaroslaw Piersa, Tymoteusz Krumholc and Katarzyna Beksa

Best Practices for Data-Efficient Modeling in NLG: How to Train Production-Ready Neural Models with Less Data Ankit Arun, Soumya Batra, Vikas Bhardwaj, Ashwini Challa, Pinar Donmez, Peyman Heidari, Hakan Inan, Shashank Jain, Anuj Kumar, Shawn Mei, Karthik Mohan and Michael White

Interactive Question Clarification in Dialogue via Reinforcement Learning Xiang Hu, Zujie Wen, Yafang Wang, Xiaolong Li and Gerard de Melo

Towards building a Robust Industry-scale Question Answering System Rishav Chakravarti, Anthony Ferritto, Bhavani Iyer, Lin Pan, Radu Florian, Salim Roukos and Avi Sil

Delexicalized Paraphrase Generation Boya Yu, Konstantine Arkoudas and Wael Hamza

16:00 - 16:30    Session DEMO1 - Tools useful in research and everyday use. Demos - Exhibition Room El Born Chair: Michal Ptaszynski

An Online Readability Leveled Arabic Thesaurus Zhengyang Jiang, Nizar Habash and Muhamed Al Khalil

Annobot: Platform for Annotating and Creating Datasets through Conversation with a Chatbot Rafał Poświata and Michał Perełkiewicz

Arabic Curriculum Analysis Hamdy Mubarak, Shimaa Amer, Ahmed Abdelali and Kareem Darwish

DART: A Lightweight Quality-Suggestive Data-to-Text Annotation Tool Ernie Chang, Jeriah Caplinger, Alex Marin, Xiaoyu Shen and Vera Demberg

Epistolary Education in 21st Century: A System to Support Composition of E-mails by Students to Superiors in Japanese Kenji Ryu and Michal Ptaszynski

Fast Word Predictor for On-Device Application Huy Tien Nguyen, Khoi Tuan Nguyen, Anh Tuan Nguyen and Thanh Lac Thi Tran

MaintNet: A Collaborative Open-Source Library for Predictive Maintenance Language Resources Farhad Akhbardeh, Travis Desell and Marcos Zampieri

TrainX – Named Entity Linking with Active Sampling and Bi-Encoders Tom Oberhauser, Tim Bischoff, Karl Brendel, Maluna Menke, Tobias Klatt, Amy Siu, Felix Alexander Gers and Alexander Löser

XplaiNLI: Explainable Natural Language Inference through Visual Analytics Aikaterini-Lida Kalouli, Rita Sevastjanova, Valeria de Paiva, Richard Crouch and Mennatallah El-Assady

16:00 - 16:30    Session POSTER9 - Text Generation. Posters - Exhibition Room Vila Olímpica

Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer Yufang Huang1, Wentao Zhu2, Deyi Xiong3, Yiye Zhang1, Changjian Hu4, Feiyu Xu4 1Cornell University, 2NVIDIA, 3Tianjin University, 4Lenovo

Ask to Learn: A Study on Curiosity-driven Question Generation Thomas Scialom1 and Jacopo Staiano2 1reciTAL, LIP6, 2reciTAL

Formality Style Transfer with Shared Latent Space Yunli Wang1, Yu Wu2, Lili Mou3, Zhoujun Li1, WenHan Chao1 1Beihang University, 2Microsoft Research Asia, 3University of Alberta

Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication Ruize Wang1, Zhongyu Wei2, Ying Cheng3, Piji Li4, Haijun Shan5, Ji Zhang6, Qi Zhang3, Xuanjing Huang3 1Academy for Engineering and Technology, Fudan University, 2School of Data Science, Fudan University, 3Fudan University, 4Tencent AI Lab, 5Zhejiang Lab, 6Faculty of Health, Engineering and Science, University of Southern Queensland; Zhejiang Lab

Referring to what you know and do not know: Making Referring Expression Generation Models Generalize To Unseen Entities Rossana Cunha, Thiago Castro Ferreira, Adriana Pagano, Fabio Alves Federal University of Minas Gerais

Topic-driven Ensemble for Online Advertising Generation Egor Nevezhin, Nikolay Butakov, Maria Khodorchenko, Maxim Petrov, Denis Nasonov ITMO University

Retrieval-Augmented Controllable Review Generation Jihyeok Kim1, Seungtaek Choi1, Reinald Kim Amplayo2, Seung-won Hwang1 1Yonsei University, 2University of Edinburgh

Automatic Detection of Machine Generated Text: A Critical Survey Ganesh Jawahar1, Muhammad Abdul-Mageed1, Laks Lakshmanan, V.S.2 1The University of British Columbia, 2UBC

A Learning-Exploring Method to Generate Diverse Paraphrases with Multi-Objective Deep Reinforcement Learning Mingtong Liu1, Erguang Yang1, Deyi Xiong2, YUJIE ZHANG1, Yao Meng3, Changjian Hu3, Jinan Xu1, Yufeng Chen1 1Beijing Jiaotong University, 2Tianjin University, 3Lenovo

Curious Case of Language Generation Evaluation Metrics: A Cautionary Tale Ozan Caglayan, Pranava Madhyastha, Lucia Specia Imperial College London

Facts2Story: Controlling Text Generation by Key Facts Eyal Orbach and Yoav Goldberg Bar Ilan University

Story Generation with Rich Details Fangzhou Zhai, Vera Demberg, Alexander Koller Saarland University

Learning with Contrastive Examples for Data-to-Text Generation Yui Uehara1, Tatsuya Ishigaki2, Kasumi Aoki3, Hiroshi Noji4, Keiichi Goshima5, Ichiro Kobayashi3, Hiroya Takamura1, Yusuke Miyao6 1The National Institute of Advanced Industrial Science and Technology (AIST), 2National Institute of Advanced Industrial Science and Technology (AIST), 3Ochanomizu University, 4Artificial Intelligence Research Center, AIST, 5Waseda University, 6University of Tokyo

MedWriter: Knowledge-Aware Medical Text Generation Youcheng Pan1, Qingcai Chen1, Weihua Peng2, Xiaolong Wang1, Baotian Hu3, Xin Liu1, Junying Chen1, Wenxiu Zhou1 1Harbin Institute of Technology, Shenzhen, 2Baidu International Technology (Shenzhen) Co., Ltd, 3Harbin Institue of Technology, Shenzhen

Dynamic Topic Tracker for KB-to-Text Generation Zihao Fu1, Lidong Bing2, Wai Lam1, Shoaib Jameel3 1The Chinese University of Hong Kong, 2Alibaba DAMO Academy, 3University of Essex

Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation Ruizhe Li1, Xiao Li2, Guanyi Chen3, Chenghua Lin4 1University of Sheffield, 2Aberdeen University, 3Utrecht University, 4Department of Computer Science, University of Sheffield

GenWiki: A Dataset of 1.3 Million Content-Sharing Text and Graphs for Unsupervised Graph-to-Text Generation Zhijing Jin1, Qipeng Guo2, Xipeng Qiu2, Zheng Zhang3 1Max Planck Institute, 2Fudan University, 3NYU Shanghai

16:30 - 17:00    Session LONG15 - Dialogue and Language Generation - Room El Raval Chair: Michael White Co-Chair: Anna Liednikova

Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity Hamza Harkous1, Isabel Groves2, Amir Saffari2 1Amazon Alexa, 2Amazon

Graph-Based Knowledge Integration for Question Answering over Dialogue Jian Liu1, Dianbo Sui2, Kang Liu2, Jun Zhao3 1Beijing Jiaotong University, 2Institute of Automation, Chinese Academy of Sciences, 3Chinese Academy of Sciences

A hierarchical approach to vision-based language generation: from simple sentences to complex natural language Simion-Vlad Bogolin, Ioana Croitoru, Marius Leordeanu Institute of Mathematics of the Romanian Academy

Sentiment Forecasting in Dialog Zhongqing Wang1, Xiujun Zhu1, Yue Zhang2, Shoushan Li1, Guodong Zhou1 1Soochow University, 2Westlake University

I Know What You Asked: Graph Path Learning using AMR for Commonsense Reasoning Jungwoo Lim1, Dongsuk Oh2, Yoonna Jang2, Kisu Yang1, Heuiseok Lim1 1Korea University, 2Department of Computer Science and Engineering, Korea University

16:30 - 17:00    Session LONG16 - Dependency Parsing - Room Montjuïc Chair: Carlos Gómez-Rodríguez Co-Chair: Philipp Dufter

Bracketing Encodings for 2-Planar Dependency Parsing Michalina Strzyz, David Vilares, Carlos Gómez-Rodríguez Universidade da Coruña

Semi-Supervised Dependency Parsing with Arc-Factored Variational Autoencoding Ge Wang and Kewei Tu ShanghaiTech University

Multitask Easy-First Dependency Parsing: Exploiting Complementarities of Different Dependency Representations Yash Kankanampati1, Joseph Le Roux2, Nadi Tomeh3, Dima Taji4, Nizar Habash4 1Indian Institute of Technology - Dhanbad, 2Université Sorbonne Paris Nord, 3LIPN, Université Sorbonne Paris Nord, 4New York University Abu Dhabi

Context Dependent Semantic Parsing: A Survey Zhuang Li, Lizhen Qu, Gholamreza Haffari Monash University

A Survey of Unsupervised Dependency Parsing Wenjuan Han1, Yong Jiang2, Hwee Tou Ng1, Kewei Tu3 1National University of Singapore, 2Alibaba DAMO Academy, 3ShanghaiTech University

16:30 - 17:00    Session LONG17 - Question Answering - Room Gràcia Chair: Christian Suess

Exploring Question-Specific Rewards for Generating Deep Questions Yuxi Xie1, Liangming Pan2, Dongzhe Wang3, Min-Yen Kan2, Yansong Feng1 1Peking University, 2National University of Singapore, 3Rakuten Institute of Technology Singapore, Rakuten Asia.

CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering Junru Lu1, Gabriele Pergola1, Lin Gui1, Binyang Li2, Yulan He1 1University of Warwick, 2University of International Relations

Improving Conversational Question Answering Systems after Deployment using Feedback-Weighted Learning Jon Ander Campos1, Kyunghyun Cho2, Arantxa Otegi3, Aitor Soroa4, Eneko Agirre1, Gorka Azkune5 1University of the Basque Country (UPV/EHU), 2New York University, 3University of the Basque Country UPV/EHU, 4University of the Basque Country, 5University of Basque Country

Modelling Long-distance Node Relations for KBQA with Global Dynamic Graph Xu Wang1, Shuai Zhao2, Jiale Han2, Bo Cheng2, Hao Yang3, Jianchang Ao4, Zhenzi Li4 1Beijing University of Posts and Telecommunications，State Key Laboratory of Networking and Switching Technology, 2Beijing University of Posts and Telecommunications, 3Huawei Co. Ltd, 42012 Labs ,Huawei Technologies CO., LTD

Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources Qianglong Chen1, Feng Ji2, Haiqing Chen3, Yin Zhang1 1Zhejiang University, 2Alibaba Group, 3Alibaba

16:30 - 17:00    Session POSTER10 - Reading comprehension and Spoken Language Understanding. Posters - Exhibition Room Vila Olímpica

A Vietnamese Dataset for Evaluating Machine Reading Comprehension Kiet Nguyen, Vu Nguyen, Anh Nguyen, Ngan Nguyen University of Information Technology, VNU-HCM

Improving Spoken Language Understanding by Wisdom of Crowds Koichiro Yoshino1, Kana Ikeuchi2, Katsuhito Sudoh3, Satoshi Nakamura4 1RIKEN Robotics, Nara Institute of Science and Technology, 2Nara Institute of Science and Technology, 3Nara Institute of Science and Technology (NAIST), 4Nara Institute of Science and Technology and RIKEN AIP Center

Bi-directional CognitiveThinking Network for Machine Reading Comprehension Wei Peng, Yue Hu, Luxi Xing, Yuqiang Xie, Jing Yu, Yajing Sun, Xiangpeng Wei Institute of Information Engineering, Chinese Academy of Sciences

Learn with Noisy Data via Unsupervised Loss Correction for Weakly Supervised Reading Comprehension Xuemiao Zhang1, Kun Zhou2, Sirui Wang3, Fuzheng Zhang3, Zhongyuan Wang4, Junfei Liu5 1School of Software and Microelectronics, Peking University, Beijing, 2Renmin University of China, 3Meituan-Dianping Group, 4Meituan, 5National Engineering Research Center for Software Engineering, Peking University, Beijing, China

Incorporating Syntax and Frame Semantics in Neural Network for Machine Reading Comprehension Shaoru Guo1, Yong Guan1, Ru Li2, Xiaoli Li3, Hongye Tan4 1Shanxi University, 2School of Computer and Information Technology，Shanxi University, 3Institute for Infocomm Research/Nanyang Technological University, 4School of Computer Science and Info. Tech. of Shanxi University

Molweni: A Challenge Multiparty Dialogues-based Machine Reading Comprehension Dataset with Discourse Structure Jiaqi Li1, Ming Liu1, Min-Yen Kan2, Zihao Zheng3, Zekun Wang1, Wenqiang Lei2, Ting Liu1, Bing Qin1 1Harbin Institute of Technology, 2National University of Singapore, 3Harbin institution of technology

Joint Event Extraction with Hierarchical Policy Network Peixin Huang1, Xiang Zhao1, Ryuichi Takanobu2, Zhen Tan3, Weidong Xiao1 1National University of Defense Technology, 2Tsinghua University, 3NUDT

Automated Graph Generation at Sentence Level for Reading Comprehension Based on Conceptual Graphs Wan-Hsuan Lin and Chun-Shien Lu Academia Sinica

ForceReader: a BERT-based Interactive Machine Reading Comprehension Model with Attention Separation zheng chen and kangjian wu University of Electronic Science and Technology of China

NUT-RC: Noisy User-generated Text-oriented Reading Comprehension Rongtao Huang1, Bowei Zou2, Yu Hong3, Wei Zhang4, AiTi Aw5, Guodong Zhou3 1Natural Language Processing Lab, Soochow University, 2Institute for Infocomm Research, ASTAR, 3Soochow University, 4Alibaba Group, 5Institute for Infocomm Research

To What Degree Can Language Borders Be Blurred In BERT-based Multilingual Spoken Language Understanding? Quynh Do1, Judith Gaspers2, Tobias Roeding2, Melanie Bradford2 1Amazon AI, 2Amazon

Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation Junhao Liu1, Linjun Shou2, Jian Pei3, Ming Gong4, Min Yang1, Daxin Jiang2 1Chinese Academy of Sciences, 2STCA NLP Group, Microsoft, 3Simon Fraser University, 4STCA NLP Group, Microsoft (China)

Neural Networks approaches focused on French Spoken Language Understanding: application to the MEDIA Evaluation Task Sahar Ghannay1, Christophe Servan2, Sophie Rosset1 1Université Paris-Saclay, CNRS, LIMSI, 2Qwant

Syntactic Graph Convolutional Network for Spoken Language Understanding Keqing He1, Shuyu Lei1, Yushu Yang2, Huixing Jiang2, Zhongyuan Wang2 1Beijing University of Posts and Telecommunications, 2Meituan-Dianping Group

Conversational Machine Comprehension: a Literature Review Somil Gupta1, Bhanu Pratap Singh Rawat2, hong yu3 1University of Massachusetts Amherst, 2University of Massachusetts, 3University of Massachusetts, Lowell

Robust Machine Reading Comprehension by Learning Soft labels Zhenyu Zhao1, Shuangzhi Wu2, Muyun Yang1, Kehai Chen3, Tiejun Zhao1 1Harbin Institute of Technology, 2Tencent, 3National Institute of Information and Communications Technology

17:00 - 17:30    Session LONG18 - Language Generation 2 - Room El Raval Chair: Sina Zarriess

Reinforced Multi-task Approach for Multi-hop Question Generation Deepak Gupta1, Hardik Chauhan2, Ravi Tej Akella3, Asif Ekbal1, Pushpak Bhattacharyya4 1IIT Patna, 2IIT, Roorkee, 3Indian Institute of Technology Roorkee, 4Indian Institute of Technology Bombay and Patna

Knowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge Bases Sheng Bi1, Xiya Cheng1, Yuan-Fang Li2, Yongzhen Wang3, Guilin Qi1 1Southeast University, 2Monash University, 3Indiana University Bloomington

Adapting a Language Model for Controlled Affective Text Generation Tushar Goswamy1, Ishika Singh2, Ahsan Barkati1, Ashutosh Modi2 1IIT Kanpur, 2Indian Institute of Technology Kanpur

Generating Instructions at Different Levels of Abstraction Arne Köhn, Julia Wichlacz, Álvaro Torralba, Daniel Höller, Jörg Hoffmann, Alexander Koller Saarland University

"Judge me by my \underline{size} (noun), do you?'' YodaLib: A Demographic-Aware Humor Generation Framework Aparna Garimella1, Carmen Banea2, Nabil Hossain3, Rada Mihalcea4 1Adobe Research, 2Initium AI Inc., 3University of Rochester, 4University of Michigan

17:00 - 17:30    Session LONG19 - Morphology - Room Montjuïc Chair: Claudia Borg Co-Chair: Garrett Nicolai

Does Chinese BERT Encode Word Structure? Yile Wang1, Leyang Cui2, Yue Zhang3 1Zhejiang University, Westlake University, 2Zhejiang University , Westlake University, 3Westlake University

Noise Isn't Always Negative: Countering Exposure Bias in Sequence-to-Sequence Inflection Models Garrett Nicolai and Miikka Silfverberg University of British Columbia

Morphologically Aware Word-Level Translation Paula Czarnowska1, Sebastian Ruder2, Ryan Cotterell3, Ann Copestake1 1University of Cambridge, 2DeepMind, 3ETH Zürich

Analogy Models for Neural Word Inflection Ling Liu1 and Mans Hulden2 1University of Colorado Boulder, 2University of Colorado

Computational Modeling of Affixoid Behavior in Chinese Morphology Yu-Hsiang Tseng, Shu-Kai HSIEH, Pei-Yi Chen, Sara Court Graduate Institute of Linguistics, National Taiwan University

17:00 - 17:30    Session LONG20 - Applications 2 - Room Gràcia Chair: Paul Rayson Co-Chair: Andrey Kutuzov

One Comment from One Perspective: An Effective Strategy for Enhancing Automatic Music Comment Tengfei Huo1, Zhiqiang Liu2, Jinchao Zhang3, Jie Zhou4 1CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences (CAS); School of Computer Science and Technology, The University of CAS, 2WeChat AI - Pattern Recognition Center Tencent Inc, 3Pattern Recognition Center, WeChat AI, Tencent, 4Tencent Inc.

A Tale of Two Linkings: Dynamically Gating between Schema Linking and Structural Linking for Text-to-SQL Parsing Sanxing Chen1, Aidan San1, Xiaodong Liu2, Yangfeng Ji1 1University of Virginia, 2Microsoft Research

Autoregressive Affective Language Forecasting: A Self-Supervised Task Matthew Matero and H. Andrew Schwartz Stony Brook University

Solving Math Word Problems with Multi-Encoders and Multi-Decoders Yibin Shen and Cheqing Jin East China Normal University

17:00 - 17:30    Session POSTER11 - Semantics 2. Posters - Exhibition Room Vila Olímpica

End to End Chinese Lexical Fusion Recognition with Sememe Knowledge Yijiang Liu1, Meishan Zhang2, Donghong Ji1 1Wuhan University, 2Tianjin University, China

Comparison by Conversion: Reverse-Engineering UCCA from Syntax and Lexical Semantics Daniel Hershcovich1, Nathan Schneider2, Dotan Dvir3, Jakob Prange2, Miryam de Lhoneux1, Omri Abend4 1University of Copenhagen, 2Georgetown University, 3Hebrew University of Jerusalem, 4The Hebrew University of Jerusalem

Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification Juan Li, Ruoxu Wang, Ningyu Zhang, Wen Zhang, Fan Yang, Huajun Chen Zhejiang University

Semantic Role Labeling with Heterogeneous Syntactic Knowledge Qingrong Xia1, Rui Wang2, Zhenghua Li1, Yue Zhang2, Min Zhang3 1Soochow University, 2Alibaba Group, 3Suda

Normalizing Compositional Structures Across Graphbanks Lucia Donatelli1, Jonas Groschwitz1, Matthias Lindemann2, Alexander Koller1, Pia Weißenhorn1 1Saarland University, 2University of Edinburgh

Leveraging WordNet Paths for Neural Hypernym Prediction Yejin Cho1, Juan Diego Rodriguez2, Yifan Gao3, Katrin Erk1 1University of Texas at Austin, 2Applied Research Laboratories, The University of Texas at Austin, 3the University of Texas at Austin

When Beards Start Shaving Men: A Subject-object Resolution Test Suite for Morpho-syntactic and Semantic Model Introspection Patricia Fischer, Daniël de Kok, Erhard Hinrichs University of Tübingen

Modality Enriched Neural Network for Metaphor Detection Mingyu WAN1 and Baixi Xing2 1The Hong Kong Polytechnic University, 2School of Information Science Language, Beijing Language and Culture University

Coordination Boundary Identification without Labeled Data for Compound Terms Disambiguation Yuya Sawada1, Takashi Wada2, Takayoshi Shibahara1, Hiroki Teranishi1, Shuhei Kondo1, Hiroyuki Shindo1, Taro Watanabe1, Yuji Matsumoto3 1Nara Institute of Science and Technology, 2School of Computing and Information Systems, The University of Melbourne, 3Riken Center for Advanced Intelligence Project

Learning Semantic Correspondences from Noisy Data-text Pairs \\by Local-to-Global Alignments Feng Nie1, Jinpeng Wang2, Chin-Yew Lin3 1sysu.edu.cn, 2Microsoft Research, Beijing, China, 3Microsoft Research

Definition Frames: Using Definitions for Hybrid Concept Representations Evangelia Spiliopoulou1, Artidoro Pagnoni1, Eduard Hovy2 1Carnegie Mellon University, 2CMU

QANom: Question-Answer driven SRL for Nominalizations Ayal Klein1, Jonathan Mamou2, Valentina Pyatkin3, Daniela Stepanov4, Hangfeng He5, Dan Roth5, Luke Zettlemoyer6, Ido Dagan3 1Bar Ilan University, 2Intel Labs, 3Bar-Ilan University, 4Recruit Institute of Technology, 5University of Pennsylvania, 6University of Washington; Facebook

Event Coreference Resolution with their Paraphrases and Argument-aware Embeddings Yutao Zeng1, Xiaolong Jin2, Saiping Guan3, Jiafeng Guo2, Xueqi Cheng2 1‎Institute of Computing Technology, Chinese Academy of Sciences, 2Institute of Computing Technology, Chinese Academy of Sciences, 3School of Computer Science and Technology, University of Chinese Academy of Sciences; CAS Key Laboratory of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences

Studying Taxonomy Enrichment on Diachronic WordNet Versions Irina Nikishina1, Varvara Logacheva2, Alexander Panchenko3, Natalia Loukachevitch4 1Skoltech, 2Skolkovo Institute of Science and Technology, 3Skolkovo Institue of Science and Technology, 4Lomonosov Moscow State University

17:30 - 18:00    Session LONG21 - Multimodality 2 - Room El Raval Chair: Helen Meng Co-Chair: Samridhi Choudhary

VICTR: Visual Information Captured Text Representation for Text-to-Vision Multimodal Tasks Caren Han, SIQU LONG, Siwen Luo, Kunze Wang, Josiah Poon University of Sydney

Finding the Evidence: Localization-aware Answer Prediction for Text Visual Question Answering Wei Han, Hantao Huang, Tao Han MediaTek Inc.

Interactive Key-Value Memory-augmented Attention for Image Paragraph Captioning Chunpu Xu1, Yu Li2, Chengming Li3, Xiang Ao4, Min Yang5, Jinwen Tian6 1Shenzhen Institutes of Advanced Technology, Chinese Academy of Science, 2Shanghai Jiaotong University, 3Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, 4Institute of Computing Technology, Chinese Academy of Sciences, 5Chinese Academy of Sciences, 6Huazhong University of Science and Technology

Geo-Aware Image Caption Generation Sofia Nikiforova, Tejaswini Deoskar, Denis Paperno, Yoad Winter Utrecht University

Bridge the Gap: High-level Semantic Planning for Image Captioning Chenxi Yuan1, Yang Bai1, Chun Yuan2 1Tsinghua University, 2Tsinghua Shenzhen International Graduate School

17:30 - 18:00    Session LONG22 - Machine Learning 2 - Room Montjuïc Chair: Matthias Gallé Co-Chair: Zhijing Jin

Interactively-Propagative Attention Learning for Implicit Discourse Relation Recognition Huibin Ruan1, Yu Hong1, Yang Xu2, Zhen Huang3, Guodong Zhou1, Min Zhang4 1Soochow University, 2Baidu.com, 3National University of Defense Technology, 4Suda

Dual Attention Model for Citation Recommendation Yang Zhang and Qiang Ma Kyoto University

Dual Attention Network for Cross-lingual Entity Alignment Jian Sun1, Yu Zhou2, Chengqing Zong3 1University of Chinese Academy of Sciences, 2CASIA, 3Institute of Automation, Chinese Academy of Sciences

Task-Aware Representation of Sentences for Generic Text Classification Kishaloy Halder1, Alan Akbik2, Josip Krapac1, Roland Vollgraf1 1Zalando Research, 2Humboldt-Universität zu Berlin

RANCC: Rationalizing Neural Networks via Concept Clustering Housam Khalifa Bashier1, Mi-Young Kim2, Randy Goebel2 1Alberta Machine Intelligence Institute, Department of Computing Science,University of Alberta, 2University of Alberta

17:30 - 18:00    Session POSTER12 - Semantics 3. Posters - Exhibition Room Vila Olímpica

LadaBERT: Lightweight Adaptation of BERT through Hybrid Model Compression Yihuan Mao1, Yujing Wang2, Chufan Wu1, Chen Zhang2, Yang Wang3, Quanlu Zhang4, Yaming Yang2, Yunhai Tong5, Jing Bai4 1Tsinghua University, 2Microsoft Research Asia, 3Beijing Institute of Technology, 4Microsoft, 5Peking University

Emotion Classification by Jointly Learning to Lexiconize and Classify Deyu Zhou1, Shuangzhi Wu2, Qing Wang3, Jun Xie4, Zhaopeng Tu5, Mu Li6 1South China University of Technology, 2Tencent, 3University of Illinois at Urbana Champaign, 4Alibaba, 5Tencent AI Lab, 6Tencent Inc.

Multi-level Alignment Pretraining for Multi-lingual Semantic Parsing Bo Shao1, Yeyun Gong2, Weizhen Qi3, Nan Duan2, Xiaola Lin1 1Sun Yat-sen University, 2Microsoft Research Asia, 3University of Science and Technology of China

Transformation of Dense and Sparse Text Representations Wenpeng Hu1, Mengyu Wang2, Bing Liu2, Feng Ji3, Jinwen Ma2, Dongyan Zhao4 1School of Mathematical Sciences, Peking University, 2Peking University, 3Alibaba Group, 4pku.edu.cn

Conception: Multilingually-Enhanced, Human-Readable Concept Vector Representations Simone Conia and Roberto Navigli Sapienza University of Rome

What Does This Acronym Mean? Introducing a New Dataset for Acronym Identification and Disambiguation Amir Pouran Ben Veyseh1, Franck Dernoncourt2, Quan Hung Tran2, Thien Huu Nguyen1 1University of Oregon, 2Adobe Research

Sentence Matching with Syntax- and Semantics-Aware BERT Tao Liu1, Xin Wang2, Chengguo Lv3, Ranran Zhen3, Guohong Fu4 1Heilongjiang University, 2CuraCloud Corporation, Seattle, WA, USA,, 3Heilongjiang University, 4Soochow University

Temporal Relations Annotation and Extrapolation Based on Semi-intervals and Boundig Relations Alejandro Pimentel1, Gemma Bel Enguix2, Gerardo Sierra Martínez1, Azucena Montes3 1Universidad Nacional Autónoma de México, 2Université Aix-Marseille, 3Centro Nacional de Investigación y Desarrollo Tecnológico

Homonym normalisation by word sense clustering: a case in Japanese Yo Sato1 and Kevin Heffernan2 1Satoama Language Services, 2Kwansei Gakuin University

Verbal Multiword Expression Identification: Do We Need a Sledgehammer to Crack a Nut? Caroline Pasquer1, Agata Savary1, Carlos Ramisch2, Jean-Yves Antoine3 1University of Tours, 2Aix Marseille University, CNRS, LIS, 3Tours U., LIFAT Lab

18:00 - 18:30    Session LONG23 - Semantics 2 - Room El Raval Chair: Tommaso Caselli Co-Chair: Meiqi Guo

An Unsupervised Method for Learning Representations of Multi-word Expressions for Semantic Classification Robert Vacareanu1, Marco A. Valenzuela-Escárcega2, Rebecca Sharp2, Mihai Surdeanu2 1Technical University of Cluj-Napoca, 2University of Arizona

SLICE: Supersense-based Lightweight Interpretable Contextual Embeddings Cindy ALOUI1, Carlos Ramisch2, Alexis Nasr3, Lucie Barque4 1Aix-Marseille Univ, LIS, Marseille, France, 2Aix Marseille University, CNRS, LIS, 3Aix Marseille University, 4Université Paris 13

An Empirical Study of the Downstream Reliability of Pre-Trained Word Embeddings Anthony Rios and Brandon Lwowski University of Texas at San Antonio

Sentence Analogies: Linguistic Regularities in Sentence Embeddings Xunjie Zhu1 and Gerard de Melo2 1ByteDance, 2Hasso Plattner Institute, University of Potsdam

Manifold Learning-based Word Representation Refinement Incorporating Global and Local Information Wenyu Zhao1, Dong Zhou1, LIN LI2, Jinjun Chen3 1Hunan University of Science and Technology, 2Wuhan University of Technology, 3Swinburne University of Technology

18:00 - 18:30    Session SHORT4 - Scarce data and low resourced languages. Short papers - Room Montjuïc Chair: Marc Schulder Co-Chair: Rolando Coto-Solano

Collective Wisdom: Improving Low-resource Neural Machine Translation using Adaptive Knowledge Distillation Fahimeh Saleh, Wray Buntine, Gholamreza Haffari Monash University

Enabling Interactive Transcription in an Indigenous Community Eric Le Ferrand1, Steven Bird1, Laurent Besacier2 1Charles Darwin University, 2LIG

Optimizing Transformer for Low-Resource Neural Machine Translation Ali Araabi and Christof Monz University of Amsterdam

Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks Lichao Sun1, Congying Xia1, Wenpeng Yin2, Tingting Liang3, Philip Yu4, Lifang He5 1University of Illinois at Chicago, 2Salesforce Research, 3Hangzhou Dianzi University, 4Universtiy of Illinois at Chicago, 5Lehigh University

Handling Anomalies of Synthetic Questions in Unsupervised Question Answering Giwon Hong1, Junmo Kang2, Doyeon Lim2, Sung-Hyon Myaeng3 1KAIST School of Computing, 2KAIST, 3School of Computing, KAIST

Designing Templates for Eliciting Commonsense Knowledge from Pretrained Sequence-to-Sequence Models Jheng-Hong Yang1, Sheng-Chieh Lin2, Rodrigo Nogueira1, Ming-Feng Tsai3, Chuan-Ju Wang2, Jimmy Lin1 1University of Waterloo, 2Academia Sinica, 3National Chengchi University

Towards the First Machine Translation System for Sumerian Transliterations Ravneet Punia1, Niko Schenk2, Christian Chiarcos3, Émilie Pagé-Perron4 1Delhi Technological University, 2Amazon, 3Goethe-Universität Frankfurt am Main, 4University of Toronto

Using Bilingual Patents for Translation Training John Lee, Benjamin Tsou, Tianyuan Cai City University of Hong Kong

18:00 - 18:30    Session LONG24 - Speech - Room Gràcia Chair: Antonios Anastasopoulos

Federated Learning for Spoken Language Understanding Zhiqi Huang, Fenglin Liu, Yuexian Zou Peking University

Attentively Embracing Noise for Robust Latent Representation in BERT Gwenaelle Cunha Sergio, Dennis Singh Moirangthem, Minho Lee Kyungpook National University

A Comprehensive Evaluation of Incremental Speech Recognition and Diarization for Conversational AI Angus Addlesee, Yanchao Yu, Arash Eshghi Heriot-Watt University

Decolonising Speech and Language Technology Steven Bird Charles Darwin University

Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation Hang Le1, Juan Pino2, Changhan Wang3, Jiatao Gu3, Didier Schwab4, Laurent Besacier5 1Université Grenoble Alpes, CNRS, LIG, 2Facebook, 3Facebook AI Research, 4Univ. Grenoble Alpes, 5LIG

18:00 - 18:30    Session POSTER13 - Machine Learning. Posters - Exhibition Room Vila Olímpica

Multitask Learning-Based Neural Bridging Reference Resolution Juntao Yu and Massimo Poesio Queen Mary University of London

Improving Human-Labeled Data through Dynamic Automatic Conflict Resolution David Q. Sun, Hadas Kotek, Christopher Klein, Mayank Gupta, William Li, Jason D. Williams Apple

Automatic Discovery of Heterogeneous Machine Learning Pipelines: An Application to Natural Language Processing Suilan Estevez-Velarde1, Yoan Gutiérrez2, Andres Montoyo2, Yudivián Almeida Cruz3 1University of Havana, 2University of Alicante, 3Havana University

Distill and Replay for Continual Language Learning Jingyuan Sun1, Shaonan Wang2, Jiajun Zhang3, Chengqing Zong1 1Institute of Automation, Chinese Academy of Sciences, 2National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 3Institute of Automation Chinese Academy of Sciences

Incorporating Noisy Length Constraints into Transformer with Length-aware Positional Encodings Yui Oka1, Katsuki Chousa1, Katsuhito Sudoh2, Satoshi Nakamura3 1Nara Institute of Science and Technology, 2Nara Institute of Science and Technology (NAIST), 3Nara Institute of Science and Technology and RIKEN AIP Center

Rethinking Skip Connection with Layer Normalization Fenglin Liu, Xuancheng Ren, Zhiyuan Zhang, Xu SUN, Yuexian Zou Peking University

Specializing Word Vectors by Spectral Decomposition on Heterogeneously Twisted Graphs Yuanhang Ren1 and Ye Du2 1University of Electronic Science and Technology of China, 2Southwestern University of Finance and Economics, China

Deep Inside-outside Recursive Autoencoder with All-span Objective Ruyue Hong, Jiong Cai, Kewei Tu ShanghaiTech University

Cross-Lingual Document Retrieval with Smooth Learning Jiapeng Liu1, Xiao Zhang2, Dan Goldwasser1, Xiao Wang1 1Purdue University, 2Amazon

Increasing Learning Efficiency of Self-Attention Networks through Direct Position Interactions, Learnable Temperature, and Convoluted Attention Philipp Dufter1, Martin Schmitt1, Hinrich Schütze2 1Center for Information and Language Processing, LMU Munich, 2Center for Information and Language Processing, University of Munich

Picking BERT's Brain: Probing for Linguistic Dependencies in Contextualized Embeddings Using Representational Similarity Analysis Michael Lepori and R. Thomas McCoy Johns Hopkins University

The Devil is in the Details: Evaluating Limitations of Transformer-based Methods for Granular Tasks Brihi Joshi1, Neil Shah2, Francesco Barbieri3, Leonardo Neves4 1Indraprastha Institute of Information Technology, Delhi, 2snap inc, 3Snap Inc., 4Snap Research

CoLAKE: Contextualized Language and Knowledge Embedding Tianxiang Sun1, Yunfan Shao1, Xipeng Qiu1, Qipeng Guo1, Yaru Hu1, Xuanjing Huang1, Zheng Zhang2 1Fudan University, 2NYU Shanghai

Invertible Tree Embeddings using a Cryptographic Role Embedding Scheme Coleman Haley and Paul Smolensky Johns Hopkins University

18:30 - 19:00    Session LONG25 - Semantics 3 - Room Montjuïc Chair: Goran Glavas Co-Chair: Alyssa Lees

Synonym Knowledge Enhanced Reader for Chinese Idiom Reading Comprehension Siyu Long1, Ran Wang1, Kun Tao1, Jiali Zeng2, Xinyu Dai1 1National Key Laboratory for Novel Software Technology, Nanjing University, 2Tencent Technology Co., Ltd, Beijing, China

Target Word Masking for Location Metonymy Resolution Haonan Li1, Maria Vasardani2, Martin Tomko1, Timothy Baldwin1 1The University of Melbourne, 2RMIT

Bridging Resolution: A Survey of the State of the Art Hideo Kobayashi1 and Vincent Ng2 1The University of Texas at Dallas, 2University of Texas at Dallas

An analysis of language models for metaphor recognition Arthur Neidlein, Philip Wiesenbach, Katja Markert Heidelberg University

What Meaning-Form Correlation Has to Compose With: A Study of MFC on Artificial and Natural Language Timothee Mickus1, Timothée Bernard2, Denis Paperno3 1Université de Lorraine, ATILF, 2Université de Paris, 3Utrecht University

18:30 - 19:00    Session PANEL1 - PANEL 1 (live): Should GPT-3 Have the Right to Free Speech? - Room El Raval Chair: Robert Dale

Robert Dale1, Emily Bender2, Pascale Fung3, Christopher Potts4 1Language Technology Group, 2University of Washington, 3Hong Kong University of Science and Technology, 4Stanford University

18:30 - 19:00    Session POSTER14 - Parsing. Posters - Exhibition Room Vila Olímpica

Evaluating Pretrained Transformer-based Models on the Task of Fine-Grained Named Entity Recognition Cedric Lothritz, Kevin Allix, Lisa Veiber, Tegawendé F. Bissyandé, Jacques Klein University of Luxembourg

Seeing Both the Forest and the Trees: Multi-head Attention for Joint Classification on Different Compositional Levels Miruna Pislar1 and Marek Rei2 1University of Cambridge, 2Imperial College London

A Unifying Theory of Transition-based and Sequence Labeling Parsing Carlos Gómez-Rodríguez, Michalina Strzyz, David Vilares Universidade da Coruña

Unleashing the Power of Neural Discourse Parsers - A Context and Structure Aware Approach Using Large Scale Pretraining Grigorii Guz, Patrick Huber, Giuseppe Carenini University of British Columbia

Semi-supervised Domain Adaptation for Dependency Parsing via Improved Contextualized Word Representations Ying Li, Zhenghua Li, Min Zhang Soochow University

Data Augmentation via Subtree Swapping for Dependency Parsing of Low-Resource Languages Mathieu Dehouck and Carlos Gómez-Rodríguez Universidade da Coruña

Porous Lattice Transformer Encoder for Chinese NER Xue Mengge1, Bowen Yu2, Tingwen Liu2, Yue Zhang3, Erli Meng4, Bin Wang5 1Institute of Information Engineering，Chinese Academy of Sciences, 2Institute of Information Engineering, Chinese Academy of Sciences, 3Westlake University, 4Xiaomi Inc., 5Xiaomi AI Lab

Learning to Prune Dependency Trees with Rethinking for Neural Relation Extraction Bowen Yu1, Xue Mengge2, Zhenyu Zhang1, Tingwen Liu1, Wang Yubin2, Bin Wang3 1Institute of Information Engineering, Chinese Academy of Sciences, 2Institute of Information Engineering，Chinese Academy of Sciences, 3Xiaomi AI Lab

How Far Does BERT Look At: Distance-based Clustering and Analysis of BERT's Attention Yue Guan1, Jingwen Leng1, Chao Li2, Quan Chen1, Minyi Guo1 1Shanghai Jiao Tong University, 2SJTU

An Analysis of Simple Data Augmentation for Named Entity Recognition Xiang Dai1 and Heike Adel2 1University of Sydney, 2Bosch Center for Artificial Intelligence

Semi-supervised Autoencoding Projective Dependency Parsing Xiao Zhang1 and Dan Goldwasser2 1Amazon, 2Purdue University

Towards Instance-Level Parser Selection for Cross-Lingual Transfer of Dependency Parsers Robert Litschko1, Ivan Vulić2, Željko Agić3, Goran Glavaš1 1University of Mannheim, 2University of Cambridge, 3Unity Technologies

Learning from Non-Binary Constituency Trees via Tensor Decomposition Daniele Castellana and Davide Bacciu Università di Pisa

Second-Order Unsupervised Neural Dependency Parsing Songlin Yang1, Yong Jiang2, Wenjuan Han3, Kewei Tu1 1ShanghaiTech University, 2Alibaba DAMO Academy, 3National University of Singapore

19:30 - 20:00    Session SOCIAL3 - North Africans in NLP Social Event

Thursday, December 10, 2020

14:30 - 15:30    INVITED TALK 3 - Room Poblenou Chair: Joakim Nivre

Neural networks as cognitive models of syntax Tal Linzen Assistant Professor of Linguistics and Data Science Director of the Computation and Psycholinguistics Lab New York University

15:30 - 16:00    Session LONG26 - Neural Machine Translation 1 - Room Monjtuic Chair: Constantin Orasan

Integrating Domain Terminology into Neural Machine Translation Elise Michon, Josep Crego, Jean Senellart SYSTRAN

Understanding the effects of word-level linguistic annotations in under-resourced neural machine translation Víctor M. Sánchez-Cartagena1, Juan Antonio Pérez-Ortiz2, Felipe Sánchez-Martínez1 1Universitat d'Alacant, 2Departament de Llenguatges i Sistemes Informàtics, Universitat d'Alacant

Breeding Gender-aware Direct Speech Translation Systems Marco Gaido1, Beatrice Savoldi2, Luisa Bentivogli3, Matteo Negri3, Marco Turchi3 1Fondazione Bruno Kessler, University of Trento, 2Università degli Studi di Trento, 3Fondazione Bruno Kessler

Neural Machine Translation Models with Back-Translation for the Extremely Low-Resource Indigenous Language Bribri Isaac Feldman and Rolando Coto-Solano Dartmouth College

Dynamic Curriculum Learning for Low-Resource Neural Machine Translation Chen Xu1, Bojie Hu2, Yufan Jiang1, Kai Feng1, Zeyang Wang1, shen huang3, Qi Ju3, Tong Xiao1, Jingbo Zhu1 1Northeastern University, 2Tencent Minority-Mandarin Translation, Beijing, China, 3tencent

15:30 - 16:00    Session LONG27 - Computational Linguistics and Linguistic Theories 1 - Room El Raval Chair: Elke Teich Co-Chair: Simonetta Montemagni

Real-Valued Logics for Typological Universals: Framework and Application Tillmann Dönicke1, Xiang Yu2, Jonas Kuhn3 1University of Göttingen, 2IMS, University of Stuttgart, 3University of Stuttgart

Comparative Probing of Lexical Semantics Theories for Cognitive Plausibility and Technological Usefulness António Branco1, João António Rodrigues1, Malgorzata Salawa2, Ruben Branco3, Chakaveh Saedi4 1University of Lisbon, 2AGH University of Science and Technology, 3Faculty of Sciences, University of Lisbon, 4Macquarie University, Science and Engineering Faculty, Department of Computing

CxGBERT: BERT meets Construction Grammar Harish Tayyar Madabushi1, Laurence Romain2, Dagmar Divjak3, Petar Milin4 1University of Birmingham, 2Department of Modern Languages, University of Birmingham, 3Department of Modern Languages & Department of English Language and Linguistics, The University of Birmingham, 4Department of Modern Languages, The University of Birmingham

How LSTM Encodes Syntax: Exploring Context Vectors and Semi-Quantization on Natural Text Chihiro Shibata1, Kei Uchiumi2, Daichi Mochihashi3 1Tokyo University of Technology, 2Denso IT Laboratory, 3The Institute of Statistical Mathematics

Corpus-based Identification of Verbs Participating in Verb Alternations Using Classification and Manual Annotation Esther Seyffarth1 and Laura Kallmeyer2 1Heinrich Heine University Düsseldorf, 2University of Duesseldorf

15:30 - 16:00    Session POSTER15 - Dialogue and Interactive Systems. Posters - Exhibition Room Vila Olímpica

When and Who? Conversation Transition Based on Bot-Agent Symbiosis Learning Network Yipeng Yu1, Ran Guan2, Jie Ma3, Zhuoxuan Jiang4, Jingchang Huang3 1Tencent, 2university of cambridge, 3IBM Research China, 4JD AI Research

Topic-relevant Response Generation using Optimal Transport for an Open-domain Dialog System Shuying Zhang1, Tianyu Zhao2, Tatsuya Kawahara1 1Kyoto University, 2rinna Co., Ltd.

An Iterative Emotion Interaction Network for Emotion Recognition in Conversations Xin Lu, Yanyan Zhao, Yang Wu, Yijian Tian, Huipeng Chen, Bing Qin Harbin Institute of Technology

PEDNet: A Persona Enhanced Dual Alternating Learning Network for Conversational Response Generation Bin Jiang1, Wanyue Zhou1, Jingxu Yang1, Chao Yang1, Shihan Wang2, Liang Pang3 1Hunan University, 2Utrecht University, 3Chinese Academy of Sciences

Dual Dynamic Memory Network for End-to-End Multi-turn Task-oriented Dialog Systems Jian Wang1, Junhao Liu2, Wei Bi3, Xiaojiang Liu3, Kejing He1, Ruifeng Xu4, Min Yang2 1South China University of Technology, 2Chinese Academy of Sciences, 3Tencent AI Lab, 4Harbin Institute of Technology, Shenzhen

Translation vs. Dialogue: A Comparative Analysis of Sequence-to-Sequence Modeling Wenpeng Hu1, Ran Le2, Bing Liu2, Jinwen Ma2, Dongyan Zhao3, Rui Yan2 1School of Mathematical Sciences, Peking University, 2Peking University, 3pku.edu.cn

Diverse dialogue generation with context dependent dynamic loss function Ayaka Ueyama1 and Yoshinobu Kano2 1Shizuoka University, 2Faculty of Informatics, Shizuoka University

Towards Topic-Guided Conversational Recommender System Kun Zhou1, Yuanhang Zhou1, Wayne Xin Zhao2, Xiaoke Wang1, Ji-Rong Wen1 1Renmin University of China, 2RUC

Intent Mining from past conversations for Conversational Agent Ajay Chatterjee and Shubhashis Sengupta Accenture Technology Labs

Summarize before Aggregate: A Global-to-local Heterogeneous Graph Inference Network for Conversational Emotion Recognition Dongming Sheng1, Dong Wang2, Ying Shen3, Haitao Zheng4, Haozhuang Liu5 1Department of Computer Science and Technology, Tsinghua University, Beijing, China, 2Shenzhen International Graduate School, Tsinghua University, 3Sun Yat-Sen University, 4Tsinghua University, Shenzhen International Graduate School., 5Department of Computer Science and Technology,Tsinghua University

Deconstruct to Reconstruct a Configurable Evaluation Metric for Open-Domain Dialogue Systems Vitou Phy1, Yang Zhao2, Akiko Aizawa3 1The University of Tokyo, 2IBM-Research Tokyo, Japan, 3National Institute of Informatics

Suggest me a movie for tonight: Leveraging Knowledge Graphs for Conversational Recommendation Rajdeep Sarkar1, Koustava Goswami2, Mihael Arcan3, John P. McCrae4 1Data Science Institute, NUI Galway, 2Insight Centre for Data Analytics, Data Science Institute, National University of Ireland Galway, 3National Universith of Ireland Galway, 4Insight Center for Data Analytics, National University of Ireland Galway

HiTrans: A Transformer-Based Context- and Speaker-Sensitive Model for Emotion Detection in Conversations Jingye Li1, Donghong Ji1, Fei Li2, Meishan Zhang3, Yijiang Liu1 1Wuhan University, 2University of Massachusetts Lowell, 3Tianjin University, China

A Co-Attentive Cross-Lingual Neural Model for Dialogue Breakdown Detection Qian Lin, Souvik Kundu, Hwee Tou Ng National University of Singapore

Integrating User History into Heterogeneous Graph for Dialogue Act Recognition Dong Wang1, Ziran Li2, Haitao Zheng3, Ying Shen4 1Shenzhen International Graduate School, Tsinghua University, 2Tsinghua University, 3Tsinghua University, Shenzhen International Graduate School., 4Sun Yat-Sen University

A Two-Level Interpretation of Modality in Human-Robot Dialogue Lucia Donatelli1, Kenneth Lai2, James Pustejovsky2 1Saarland University, 2Brandeis University

16:00 - 16:30    Session IND3 - INDUSTRY TRACK - Applications - Room Gràcia Chair: Elena Tutubalina

Multi-task Learning of Spoken Language Understanding by Integrating N-Best Hypotheses with Hierarchical Attention Mingda Li, Xinyue Liu, Weitong Ruan, Luca Soldaini, Wael Hamza and Chengwei Su

Misspelling Detection from Noisy Product Images Varun Nagaraj Rao and Mingwei Shen

hinglishNorm - A Corpus of Hindi-English Code Mixed Sentences for Text Normalization Piyush Makhija, Ankit Kumar and Anuj Gupta

Assessing Social License to Operate from the Public Discourse on Social Media Chang Xu, Cecile Paris, Ross Sparks, Surya Nepal and Keith VanderLinden

Extreme Model Compression for On-device Natural Language Understanding Kanthashree Mysore Sathyendra, Samridhi Choudhary and Leah Nicolich-Henkin

Scalable Cross-lingual Treebank Synthesis for Improved Production Dependency Parsers Yousef El-Kurdi, Hiroshi Kanayama, Efsun Sarioglu Kayi, Vittorio Castelli, Todd Ward and Radu Florian

16:00 - 16:30    Session ROADMAPS 2 - INDUSTRY ROADMAPS 2 (live) - Room Eixample Chair: Alexander Loeser Co-Chair: José Manuel Gómez Perez

Leveraging Chargrid and BERTgrid for document information extraction SAP

The Financial Search Engine and AI at Bloomberg Bloomberg

The Language of Fashion AI at Zalando: From Search and Customer Feedback to Outfits Zalando

Engineering at Grammarly Grammarly

16:00 - 16:30    Session POSTER16 - Machine translation. Posters - Exhibition Room Vila Olímpica

Robust Unsupervised Neural Machine Translation with Adversarial Denoising Training Haipeng Sun1, Rui Wang2, Kehai Chen3, Xugang Lu2, Masao Utiyama2, Eiichiro Sumita2, Tiejun Zhao1 1Harbin Institute of Technology, 2NICT, 3National Institute of Information and Communications Technology

Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English Gongbo Tang1, Rico Sennrich2, Joakim Nivre1 1Uppsala University, 2University of Zurich

Improving Low-Resource NMT through Relevance Based Linguistic Features Incorporation Abhisek Chakrabarty1, Raj Dabre2, Chenchen Ding2, Masao Utiyama2, Eiichiro Sumita2 1NICT, Japan, 2NICT

Layer-Wise Multi-View Learning for Neural Machine Translation Qiang Wang1, Changliang Li2, Yue Zhang3, Tong Xiao4, Jingbo Zhu4 1Northeastern University at Shenyang, China, 2Kingsoft, 3Westlake University, 4Northeastern University

Bilingual Subword Segmentation for Neural Machine Translation Hiroyuki Deguchi1, Masao Utiyama2, Akihiro Tamura3, Takashi Ninomiya1, Eiichiro Sumita2 1Ehime University, 2NICT, 3Doshisha University

Token Drop mechanism for Neural Machine Translation Huaao Zhang1, Shigui Qiu1, Xiangyu Duan1, Min Zhang2 1Soochow University, 2Suda

Supervised Visual Attention for Multimodal Neural Machine Translation Tetsuro Nishihara1, Akihiro Tamura2, Takashi Ninomiya1, Yutaro Omote1, Hideki Nakayama3 1Ehime University, 2Doshisha University, 3The University of Tokyo

Investigating Catastrophic Forgetting During Continual Training for Neural Machine Translation Shuhao Gu1 and Yang Feng2 1institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences, 2Institute of Computing Technology, Chinese Academy of Sciences

The Two Shades of Dubbing in Neural Machine Translation Alina Karakanta1, Supratik Bhattacharya2, Shravan Nayak3, Timo Baumann4, Matteo Negri5, Marco Turchi5 1Fondazione Bruno Kessler (FBK), University of Trento, 2Birla Institute of Technology and Science, 3Indian Institute of Technology (BHU), 4Universität Hamburg, 5Fondazione Bruno Kessler

Filtering Back-Translated Data in Unsupervised Neural Machine Translation Jyotsana Khatri1 and Pushpak Bhattacharyya2 1Indian Institute of Technology Bombay, Mumbai, 2Indian Institute of Technology Bombay and Patna

Lost in Back-Translation: Emotion Preservation in Neural Machine Translation Enrica Troiano1, Roman Klinger1, Sebastian Padó2 1University of Stuttgart, 2Stuttgart University

Intermediate Self-supervised Learning for Machine Translation Quality Estimation Raphael Rubino and Eiichiro Sumita NICT

Unifying Input and Output Smoothing in Neural Machine Translation Yingbo Gao, Baohao Liao, Hermann Ney RWTH Aachen University

Neural Transduction for Multilingual Lexical Translation Dylan Lewis, Winston Wu, Arya D. McCarthy, David Yarowsky Johns Hopkins University

A Document-Level Neural Machine Translation Model with Dynamic Caching Guided by Theme-Rheme Information Yiqi Tong1, Jiangbin Zheng1, Hongkang Zhu1, Yidong Chen1, xiaodong shi2 1Department of Artificial Intelligence, School of Informatics, Xiamen University, 2Xiamen University

Context-Aware Cross-Attention for Non-Autoregressive Translation Liang Ding1, Longyue Wang2, Di Wu3, Dacheng Tao4, Zhaopeng Tu2 1School of Computer Science, FEIT, The University of Sydney, 2Tencent AI Lab, 3pku.edu.cn, 4UBTECH Sydney AI Center; School of Computer Science, The University of Sydney

16:30 - 17:00    Session LONG28 - Dialogue 2 - Room El Raval Chair: Philippe Blache Co-Chair: Olga Golovneva

Does Gender Matter? Towards Fairness in Dialogue Systems Haochen Liu1, Jamell Dacon1, Wenqi Fan2, Hui Liu1, Zitao Liu3, Jiliang Tang1 1Michigan State University, 2The Hong Kong Polytechnic University, 3TAL Education Group

Combining Cognitive Modeling and Reinforcement Learning for Clarification in Dialogue Baber Khalid1, Malihe Alikhani2, Matthew Stone1 1Rutgers University, 2University of Pittsburgh

Knowledge Aware Emotion Recognition in Textual Conversations via Multi-Task Incremental Transformer Duzhen Zhang1, Xiuyi Chen1, Shuang Xu2, Bo Xu2 1Institute of Automation, Chinese Academy of Sciences., 2Institute of Automation, Chinese Academy of Sciences

MEISD: A Multimodal Multi-Label Emotion, Intensity and Sentiment Dialogue Dataset for Emotion Recognition and Sentiment Analysis in Conversations Mauajama Firdaus1, Hardik Chauhan2, Asif Ekbal1, Pushpak Bhattacharyya3 1IIT Patna, 2IIT, Roorkee, 3Indian Institute of Technology Bombay and Patna

EmpDG: Multi-resolution Interactive Empathetic Dialogue Generation Qintong Li1, Hongshen Chen2, Zhaochun Ren1, Pengjie Ren3, Zhaopeng Tu4, Zhumin CHEN1 1Shandong University, 2JD.com, 3University of Amsterdam, 4Tencent AI Lab

16:30 - 17:00    Session LONG29 - Neural Machine Translation 2 - Room Montjuïc Chair: Jiajun Zhang

Leveraging Discourse Rewards for Document-Level Neural Machine Translation Inigo Jauregi Unanue1, Nazanin Esmaili1, Gholamreza Haffari2, Massimo Piccardi1 1University of Technology Sydney, 2Monash University

Effective Use of Target-side Context for Neural Machine Translation Hideya Mino1, Hitoshi Ito1, Isao Goto2, Ichiro Yamada3, Takenobu Tokunaga4 1NHK Science & Technology Research Laboratories, 2NHK, 3Japan Broadcasting Corporation, 4Tokyo Institute of Technology

Knowledge Graph Enhanced Neural Machine Translation via Multi-task Learning on Sub-entity Granularity Yang Zhao1, Lu Xiang2, Junnan Zhu1, Jiajun Zhang3, Yu Zhou4, Chengqing Zong1 1Institute of Automation, Chinese Academy of Sciences, 2National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 3Institute of Automation Chinese Academy of Sciences, 4CASIA

Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation Bryan Eikema and Wilker Aziz University of Amsterdam

Domain Transfer based Data Augmentation for Neural Query Translation Liang Yao1, Baosong Yang2, Haibo Zhang1, Boxing Chen1, Weihua Luo3 1Alibaba, 2Alibaba Damo Academy, Alibaba Inc., 3Alibaba Group

16:30 - 17:00    Session LONG30 - Computational Linguistics and Linguistic Theories 2 - Room Gràcia Chair: Alessandro Lenci Co-Chair: Gemma Bel Engix

Living Machines: A study of atypical animacy Mariona Coll Ardanuy1, Federico Nanni1, Kaspar Beelen1, Kasra Hosseini1, Ruth Ahnert2, Jon Lawrence3, Katherine McDonough1, Giorgia Tolfo4, Daniel CS Wilson1, Barbara McGillivray5 1The Alan Turing Institute, 2Queen Mary University of London, 3University of Exeter, 4The British Library, 5Alan Turing Institute / University of Cambridge

Aspectuality Across Genre: A Distributional Semantics Approach Thomas Kober1, Malihe Alikhani2, Matthew Stone3, Mark Steedman4 1rasa Technologies GmbH, 2University of Pittsburgh, 3Rutgers University, 4University of Edinburgh

Rhetoric, Logic, and Dialectic: Advancing Theory-based Argument Quality Assessment in Natural Language Processing Anne Lauscher1, Lily Ng2, Courtney Napoles2, Joel Tetreault3 1University of Mannheim, 2Grammarly, 3Dataminr

A Linguistic Perspective on Reference: Choosing a Feature Set for Generating Referring Expressions in Context Fahime Same1 and Kees van Deemter2 1University of Cologne, 2Utrecht University

Coreference information guides human expectations during natural reading Evan Jaffe, Cory Shain, William Schuler The Ohio State University

16:30 - 17:00    Session POSTERS17 - Morphology and Segmentation. Posters - Exhibition Room Vila Olímpica

Interactive Word Completion for Morphologically Complex Languages William Lane and Steven Bird Charles Darwin University

Joint Persian Word Segmentation Correction and Zero-Width Non-Joiner Recognition Using BERT Ehsan Doostmohammadi1, Minoo Nassajian1, Adel Rahimi2 1Sharif University of Technology, 2Dathena Science Pte. Ltd.

Syllable-based Neural Thai Word Segmentation Pattarawat Chormai1, Ponrawee Prasertsom2, Jin Cheevaprawatdomrong2, Attapol Rutherford2 1Technical University of Berlin; Max Planck School of Cognition, 2Chulalongkorn University

Incorporating Inner-word and Out-word Features for Mongolian Morphological Segmentation Na Liu, Xiangdong Su, Haoran Zhang, Guanglai Gao, Feilong Bao College of Computer Science Inner Mongolia University

Morphological disambiguation from stemming data Antoine Nzeyimana University of Massachusetts Amherst

Revitalization of Indigenous Languages through Pre-processing and Neural Machine Translation: The case of Inuktitut Tan Ngoc Le and Fatiha Sadat UQAM

Semi-supervised URL Segmentation with Recurrent Neural Networks Pre-trained on Knowledge Graph Entities Hao Zhang, Jae Ro, Richard Sproat Google

Utilizing Subword Entities in Character-Level Sequence-to-Sequence Lemmatization Models Nasser Zalmout1 and Nizar Habash2 1Amazon, 2New York University Abu Dhabi

Wiktionary Normalization of Translations and Morphological Information Winston Wu and David Yarowsky Johns Hopkins University

17:00 - 17:30    Session LONG31 - Machine Translation and Transfer Learning - Room El Raval Chair: Marta Ruiz Costa-Jussà Co-Chair: Gongbo Tang

Detecting Urgency Status of Crisis Tweets: A Transfer Learning Approach for Low Resource Languages Efsun Sarioglu Kayi1, Linyong Nan2, Bohan Qu2, Mona Diab3, Kathleen McKeown4 1Columbia University/IBM Research, 2Columbia University, 3Facebook AI, 4Columbia University and Amazon (Amazon Scholar)

Cross-lingual Transfer Learning for Grammatical Error Correction Ikumi Yamashita1, Satoru Katsumata2, Masahiro Kaneko1, Aizhan Imankulova1, Mamoru Komachi1 1Tokyo Metropolitan University, 2Retrieva, Inc.

Emergent Communication Pretraining for Few-Shot Machine Translation Yaoyiran Li1, Edoardo Maria Ponti2, Ivan Vulić1, Anna Korhonen1 1University of Cambridge, 2Mila Montreal / University of Cambridge

ContraCAT: Contrastive Coreference Analytical Templates for Machine Translation Dario Stojanovski1, Benno Krojer1, Denis Peskov2, Alexander Fraser3 1LMU Munich, 2University of Maryland, 3Ludwig-Maximilians-Universität München

SpanAlign: Sentence Alignment Method based on Cross-Language Span Prediction and ILP Katsuki Chousa1, Masaaki Nagata2, Masaaki Nishino3 1NTT, 2NTT Corporation, 3NTT Communication Science Laboratories

17:00 - 17:30    Session LONG32 - Evaluation - Room Montjuïc Chair: Maja Popovic Co-Chair: Liane Guillou

CLUE: A Chinese Language Understanding Evaluation Benchmark Liang Xu1, Hai Hu2, Xuanwei Zhang3, Lu Li4, Chenjie Cao5, Yudong Li6, Yechen Xu7, Kai Sun8, Dian Yu9, Cong Yu1, Yin Tian10, Qianqian Dong11, Weitang Liu12, Bo Shi13, Yiming Cui14, Junyi Li15, Jun Zeng4, Rongzhao Wang16, Weijian Xie17, Yanting Li18, Yina Patterson19, Zuoyu Tian2, Yiwen Zhang19, He Zhou2, Shaoweihua Liu20, Zhe Zhao21, Qipeng Zhao22, Cong Yue23, Xinrui Zhang24, Zhengliang Yang25, Kyle Richardson26, Zhenzhong Lan27 1ai-indeed, 2Indiana University, 3iqiyi Inc., 4Central China Normal University, 5PingAn Gammalab, 6China University of Geosciences (Beijing), 7Zhejiang University, 8Cornell University, 9Tencent AI Lab, 10Intelligence Indeed, 11Institute of Automation, Chinese Academy of Sciences, 12zhejiang dahua technology CO.LTD, 13NLP Group, Mobvoi Inc., 14Harbin Institute of Technology, 15China Academy of Electronics and Information Technology, 16Peking University, 17Baidu Inc., 18MIT, 19Indiana University Bloomington, 20Yiwise.AI, 21Renmin University of China, 22Beijing Xinhua Multimedia Data Co.,Ltd., 23Mobvoi, 24SF Technology, 25tkonline-nlplab, 26the Allen Institute for Artificial Intelligence, 27Westlake University

A Human Evaluation of AMR-to-English Generation Systems Emma Manning, Shira Wein, Nathan Schneider Georgetown University

Identifying Annotator Bias: A new IRT-based method for bias identification Jacopo Amidei1, Paul Piwek2, Alistair Willis2 1Open University, 2The Open University

Would you describe a leopard as yellow? Evaluating crowd-annotations with justified and informative disagreement Pia Sommerauer1, Antske Fokkens2, Piek Vossen3 1Vrije Universiteit Amsterdam, 2VU Amsterdam, 3VU University Amsterdam

Manual Clustering and Spatial Arrangement of Verbs for Multilingual Evaluation and Typology Analysis Olga Majewska1, Ivan Vulić1, Diana McCarthy2, Anna Korhonen1 1University of Cambridge, 2University of Cambridge (DTAL)

17:00 - 17:30    Session LONG33 - Applications 3 - Room Gràcia Chair: Elena Cabrio Co-Chair: Chenyang Lyu

Hierarchical Trivia Fact Extraction from Wikipedia Articles Jingun Kwon1, Hidetaka Kamigaito1, Young-In Song2, Manabu Okumura1 1Tokyo Institute of Technology, 2NAVER

Predicting Clickbait Strength in Online Social Media Vijayasaradhi Indurthi1, Bakhtiyar Syed2, Manish Gupta2, Vasudeva Varma2 1International Institute of Information Technology, 2IIIT Hyderabad

GPolS: A Contextual Graph-Based Language Model for Analyzing Parliamentary Debates and Political Cohesion Ramit Sawhney1, Arnav Wadhwa2, Shivam Agarwal3, Rajiv Ratn Shah4 1Netaji Subhas Institute of Technology, 2MIDAS IIITD, 3Manipal Institute of Technology, 4IIIT Delhi

Measuring Correlation-to-Causation Exaggeration in Press Releases Bei Yu1, Jun Wang2, Lu Guo3, Yingya Li1 1Syracuse University, 2Independent Researcher, 3Sichuan University

Inflating Topic Relevance with Ideology: A Case Study of Political Ideology Bias in Social Topic Detection Models Meiqi Guo, Rebecca Hwa, Yu-Ru Lin, Wen-Ting Chung University of Pittsburgh

17:00 - 17:30    Session POSTER18 - Dialogue and understanding. Posters - Exhibition Room Vila Olímpica

A Taxonomy of Empathetic Response Intents in Human Social Conversations Anuradha Welivita and Pearl Pu École polytechnique fédérale de Lausanne

A Multitask Active Learning Framework for Natural Language Understanding Hua Zhu1, Wu Ye2, Sihan Luo2, Xidong Zhang2 1vivo Mobile Communication Co.,Ltd, 2vivo Mobile Communication Co., Ltd

Two-level classification for dialogue act recognition in task-oriented dialogues Philippe Blache1, Massina Abderrahmane2, Stéphane Rauzy3, Magalie Ochs4, Houda Oufaida5 1LPL CNRS, 2LPL & ESI, 3LPL AMU-CNRS, 4LIS AMU-CNRS, 5ESI

Balanced Joint Adversarial Training for Robust Intent Detection and Slot Filling Xu Cao1, Deyi Xiong2, Chongyang Shi3, Chao Wang4, Yao Meng5, Changjian Hu5 1Lenovo Research; Beijing Institute of Technology, 2Tianjin University, 3School of Computer Science, Beijing Institute of Technology, 4NLP&CA, AI lab, Lenovo Research, 5Lenovo

Reasoning Requirements for Indirect Speech Act Interpretation Vasanth Sarathy, Alexander Tsuetaki, Antonio Roque, Matthias Scheutz Tufts University

Understanding Unnatural Questions Improves Reasoning over Text Xiaoyu Guo, Yuan-Fang Li, Gholamreza Haffari Monash University

An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution Ryuto Konno1, Yuichiroh Matsubayashi1, Shun Kiyono2, Hiroki Ouchi3, Ryo Takahashi1, Kentaro Inui4 1Tohoku University, 2RIKEN AIP / Tohoku University, 3Riken AIP, 4Tohoku University / Riken

A Large-Scale Corpus of E-mail Conversations with Standard and Two-Level Dialogue Act Annotations Motoki Taniguchi1, Yoshihiro Ueda2, Tomoki Taniguchi3, Tomoko Ohkuma3 1Fuji Xerox, Tokyo Metropolitan University, 2Fuji Xerox Co., Ltd., 3Fuji Xerox

Intra-/Inter-Interaction Network with Latent Interaction Modeling for Multi-turn Response Selection Yang Deng, Wenxuan Zhang, Wai Lam The Chinese University of Hong Kong

Few-shot Pseudo-Labeling for Intent Detection Thomas Dopierre1, Christophe Gravier2, Julien Subercaze3, Wilfried Logerais4 1Lab Hubert Curien UMR 5516, 2Université Jean Monnet, 3Laboratoire Hubert Curien, 4Meetic

Similarity or deeper understanding? Analyzing the TED-Q dataset of evoked questions Matthijs Westera1, Jacopo Amidei2, Laia Mayol1 1Universitat Pompeu Fabra, 2Open University

Sentiment Analysis for Emotional Speech Synthesis in a News Dialogue System Hiroaki Takatsu1, Ryota Ando2, Yoichi Matsuyama1, Tetsunori Kobayashi1 1Waseda University, 2Naigai Pressclipping Bureau,Ltd.

Adversarial Learning on the Latent Space for Diverse Dialog Generation Kashif Khan1, Gaurav Sahu1, Vikash Balasubramanian1, Lili Mou2, Olga Vechtomova1 1University of Waterloo, 2University of Alberta

Inconsistencies in Crowdsourced Slot-Filling Annotations: A Typology and Identification Methods Stefan Larson1, Adrian Cheung2, Anish Mahendran3, Kevin Leach4, Jonathan K. Kummerfeld4 1(unaffiliated), 2Clinc, 3Clinc, Inc, 4University of Michigan

17:30 - 18:00    Session LONG34 - Machine Translation, Quality and Evaluation - Room El Raval Chair: Antonio Toral Co-Chair: Yingbo Gao

Online Versus Offline NMT Quality: An In-depth Analysis on English-German and German-English Maha Elbayad1, Michael Ustaszewski2, Emmanuelle Esperança-Rodier3, Francis Brunet-Manquat4, Jakob Verbeek5, Laurent Besacier6 1INRIA / LIG, 2University of Innsbruck, 3Univ. Grenoble Alpes, CNRS, Grenoble INP*, LIG, 4UGA, 5INRIA, 6LIG

Informative Manual Evaluation of Machine Translation Output Maja Popović ADAPT Centre @ DCU

TransQuest: Translation Quality Estimation with Cross-lingual Transformers Tharindu Ranasinghe1, Constantin Orasan2, Ruslan Mitkov1 1University of Wolverhampton, 2University of Surrey

Monolingual and Multilingual Reduction of Gender Bias in Contextualized Representations Sheng Liang1, Philipp Dufter1, Hinrich Schütze2 1Center for Information and Language Processing, LMU Munich, 2Center for Information and Language Processing, University of Munich

AraBench: Benchmarking Dialectal Arabic-English Machine Translation Hassan Sajjad1, Ahmed Abdelali1, Nadir Durrani2, Fahim Dalvi3 1Qatar Computing Research Institute, 2QCRI, 3Qatar Computing Research Institute, HBKU

17:30 - 18:00    Session LONG35 - Machine Learning 3 - Room Montjuïc Chair: Vincent Ng Co-Chair: Anthony Rios

Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks Trapit Bansal1, Rishikesh Jha2, Andrew McCallum3 1University of Massachusetts Amherst, 2Code for Science and Society, 3UMass Amherst

A Mixture-of-Experts Model for Learning Multi-Facet Entity Embeddings Rana Alshaikh1, Zied Bouraoui2, Shelan Jeawak3, Steven Schockaert3 1School of Computer Science and Informatics, 2CRIL-CNRS & University of Artois, 3Cardiff University

Classifier Probes May Just Learn from Linear Context Features Jenny Kunz and Marco Kuhlmann Linköping University

Priorless Recurrent Networks Learn Curiously Jeff Mitchell and Jeffrey Bowers University of Bristol

Answer-driven Deep Question Generation based on Reinforcement Learning Liuyin Wang1, Zihan Xu2, Zibo Lin3, Haitao Zheng4, Ying Shen5 1Department of Computer Science and Technology,Tsinghua University, 2Tsinghua University, 3Department of Computer Science and Technology, Tsinghua University, 4Tsinghua University, Shenzhen International Graduate School., 5Sun Yat-Sen University

17:30 - 18:00    Session POSTER19 - Textual Inference and Question Answering. Posters - Exhibition Room Vila Olímpica

Distinguishing Between Foreground and Background Events in News Mohammed Aldawsari1, Adrian Perez1, Deya Banisakher1, Mark Finlayson2 1Florida International University, 2FIU

Pick a Fight or Bite your Tongue: Investigation of Gender Differences in Idiomatic Language Usage Ella Rabinovich1, Hila Gonen2, Suzanne Stevenson3 1IBM Research, 2Bar-Ilan University, 3University of Toronto

Intra-Correlation Encoding for Chinese Sentence Intention Matching Xu Zhang1, Yifeng Li2, Wenpeng Lu1, Ping Jian3, Guoqiang Zhang4 1Qilu University of Technology (Shandong Academy of Sciences), 2Brock University, 3Beijing Institute of Technology, 4University of Technology Sydney

Explain by Evidence: An Explainable Memory-based Neural Network for Question Answering Quan Hung Tran1, Nhan Dam2, Tuan Lai3, Franck Dernoncourt1, Trung Le2, Nham Le4, Dinh Phung5 1Adobe Research, 2Monash University, 3University of Illinois at Urbana-Champaign, 4University of Waterloo, 5Monash University, Australia

A Study on Efficiency, Accuracy and Document Structure for Answer Sentence Selection Daniele Bonadiman1 and Alessandro Moschitti2 1Amazon AI, 2Amazon

Auto-Encoding Variational Bayes for Inferring Topics and Visualization Dang Pham1 and Tuan Le2 1NMSU, 2New Mexico State University

Hy-NLI: a Hybrid system for Natural Language Inference Aikaterini-Lida Kalouli1, Richard Crouch2, Valeria de Paiva3 1University of Konstanz, 2Chegg, 3Topos Institute

Identifying Motion Entities in Natural Language and A Case Study for Named Entity Recognition Ngoc Phuoc An Vo, Irene Manotas, Vadim Sheinin, Octavian Popescu IBM Research

Global Context-enhanced Graph Convolutional Networks for Document-level Relation Extraction Huiwei Zhou, Yibin Xu, Weihong Yao, Zhe Liu, Chengkun Lang, Haibin Jiang Dalian University of Technology

Diverse Keyphrase Generation with Neural Unlikelihood Training Hareesh Bahuleyan and Layla El Asri Borealis AI

User Memory Reasoning for Conversational Recommendation Hu Xu1, Seungwhan Moon2, Honglei Liu2, Bing Liu1, Pararth Shah3, Philip Yu4 1Facebook, 2Facebook Conversational AI, 3Facebook Assistant, 4Universtiy of Illinois at Chicago

Diverse and Non-redundant Answer Set Extraction on Community QA based on DPPs Shogo Fujita1, Tomohide Shibata2, Manabu Okumura1 1Tokyo institute of technology, 2Yahoo Japan Corporation

An empirical analysis of existing systems and datasets toward general simple question answering Namgi Han1, Goran Topic2, Hiroshi Noji3, Hiroya Takamura4, Yusuke Miyao5 1The Graduate University for Advanced Studies, SOKENDAI, 2AIST, 3Artificial Intelligence Research Center, AIST, 4The National Institute of Advanced Industrial Science and Technology (AIST), 5University of Tokyo

Learn to Combine Linguistic and Symbolic Information for Table-based Fact Verification Qi Shi, Yu Zhang, Qingyu Yin, Ting Liu Harbin Institute of Technology

CosMo: Conditional Seq2Seq-based Mixture Model for Zero-Shot Commonsense Question Answering Farhad Moghimifar1, Lizhen Qu2, Yue Zhuo3, Mahsa Baktashmotlagh4, Gholamreza Haffari2 1The University of Queensland, 2Monash University, 3The University of New South Wales, 4UQ

18:00 - 19:00    INVITED TALK 4 (live) - Room Poblenou Chair: Hans Uszkoreit

Genie: The Open Virtual Assistant Initiative Monica Lam Professor Computer Science Department Stanford University Faculty Director Open Virtual Assistant Lab (OVAL)

19:00 - 19:30    Session SOCIAL5 - Catalan Human Towers: Interview with a Casteller

Casteller: Gabriel Puig (Colla castellera Els Trempats / Universitat Pompeu Fabra)

19:30 - 20:00    Session SOCIAL - “Black in AI” social event

Friday, December 11, 2020

14:30 - 15:00    Session SOCIAL6 - SOCIAL EVENT: Music for COLING'2020

MACHÍN-LENIN: Collaborative exploration of poetry, music, and speech. Work commissioned by COLING 2020 Concept, artistic direction, electronics and programming by Àngel Faraldo Cinematography by Judro Guerrero Computer modified text by Gerard Altaió Voices: Iona Schneider and Gerard Altaió Piano: Haize Lizarazu Double bass: Àlex Reviriego Video Assistant: Isaac Rodriguez

15:00 - 15:30    Session INV5 - INVITED TALK 5 - Room Poblenou Chair: Nicoletta Calzolari

Ethics in the Vision and Language of Artificial Intelligence Margaret Mitchell Senior Research Scientist Google Research and Machine Intelligence

15:30 - 16:00    Session LONG36 - Summarization - Room Montjuïc Chair: Jackie Chi Kit Cheung Co-Chair: Behzad Golshan

Enhancing Extractive Text Summarization with Topic-Aware Graph Neural Networks Peng Cui, Le Hu, Yuanchao Liu Harbin Institute of Technology

SaSAKE: Syntax and Semantics Aware Keyphrase Extraction from Research Papers T.Y.S.S Santosh, Debarshi Kumar Sanyal, Plaban Kumar Bhowmick, Partha Pratim Das IIT Kharagpur

News Editorials: Towards Summarizing Long Argumentative Texts Shahbaz Syed1, Roxanne El Baff2, Johannes Kiesel3, Khalid Al Khatib3, Benno Stein3, Martin Potthast1 1Leipzig University, 2German Aerospace Center, 3Bauhaus-Universität Weimar

Automatic Interlinear Glossing for Under-Resourced Languages Leveraging Translations Xingyuan Zhao1, Satoru Ozaki1, Antonios Anastasopoulos2, Graham Neubig1, Lori Levin1 1Carnegie Mellon University, 2George Mason University

Scientific Keyphrase Identification and Classification by Pre-Trained Language Models Intermediate Task Transfer Learning Seoyeon Park and Cornelia Caragea University of Illinois at Chicago

15:30 - 16:00    Session LONG37 - Fake News and Rumours - Room El Raval Chair: John McCrae

Exploiting Microblog Conversation Structures to Detect Rumors Jiawen Li, Yudianto Sujana, Hung-Yu Kao National Cheng Kung University

Explainable Automated Fact-Checking: A Survey Neema Kotonya and Francesca Toni Imperial College London

Early Detection of Fake News by Utilizing the Credibility of News, Publishers, and Users based on Weakly Supervised Learning Chunyuan Yuan1, Qianwen Ma2, Wei Zhou3, Jizhong Han4, Songlin Hu5 1Institute of Information Engineering，Chinese Academy of Sciences, 2University of Chinese Academy of Sciences, 3University of Chinese Academy of Sciences and Institute of Information Engineering, Chinese Academy of Sciences, 4Institute of Information Engineering, Chinese Academy of Sciences, 5Institute of Information Engineering, CAS

Debunking Rumors on Twitter with Tree Transformer Jing Ma1 and Wei Gao2 1Hong Kong Baptist University, 2Singapore Management University

Words are the Window to the Soul: Language-based User Representations for Fake News Detection Marco Del Tredici1 and Raquel Fernández2 1University of Amsterdam, 2ILLC, University of Amsterdam

15:30 - 16:00    Session POSTER20 - Text Classification, Text Mining and Knowledge Extraction. Posters - Exhibition Room Vila Olímpica

Argumentation Mining on Essays at Multi Scales Hao Wang1, Zhen Huang2, Yong Dou1, Yu Hong3 1National University of Defense Technology, 2National University of DefenseTechnology, 3School of Computer Science and Technology, Soochow University

Data Augmentation for Multiclass Utterance Classification – A Systematic Study Binxia Xu1, Siyuan Qiu1, Jie Zhang1, Yafang Wang2, Xiaoyu Shen3, Gerard de Melo4 1Ant Financial Services Group, 2Alibaba, 3Max Planck Institute for Informatics, 4Hasso Plattner Institute, University of Potsdam

KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi Rubungo Andre Niyongabo1, Qu Hong2, Julia Kreutzer3, Li Huang1 1University of Electronic Science and Technology of China, 2School of Computer Science and Engineering, University of Electronic Science and Technology of China, 3Masakhane

Go Simple and Pre-Train on Domain-Specific Corpora: On the Role of Training Data for Text Classification Aleksandra Edwards, Jose Camacho-Collados, Hélène De Ribaupierre, Alun Preece Cardiff University

Unsupervised Fine-tuning for Text Clustering Shaohan Huang1, Furu Wei2, Lei Cui1, Xingxing Zhang1, Ming Zhou1 1Microsoft Research Asia, 2Microsoft Research

Exploiting Narrative Context and A Priori Knowledge of Categories in Textual Emotion Classification Hikari Tanabe, Tetsuji Ogawa, Tetsunori Kobayashi, Yoshihiko Hayashi Waseda University

Word-Level Uncertainty Estimation for Black-Box Text Classifiers using RNNs Jakob Smedegaard Andersen1, Tom Schöner2, Walid Maalej1 1University of Hamburg, 2HAW Hamburg

Few-Shot Text Classification with Edge-Labeling Graph Neural Network-Based Prototypical Network Chen Lyu, Weijie Liu, Ping Wang Peking University

ManyEnt: A Dataset for Few-shot Entity Typing Markus Eberts, Kevin Pech, Adrian Ulges RheinMain University of Applied Sciences

Embedding Meta-Textual Information for Improved Learning to Rank Toshitaka Kuwa1, Shigehiko Schamoni2, Stefan Riezler2 1Japanese Patent Office, 2Heidelberg University

Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification Timo Schick1, Helmut Schmid2, Hinrich Schütze3 1LMU Munich / Sulzer GmbH, 2CIS, Ludwig-Maximilians-Universität, 3Center for Information and Language Processing, University of Munich

Knowledge Base Embedding By Cooperative Knowledge Distillation Raphaël Sourty1, Jose G. Moreno2, François-Paul Servant3, Lynda Tamine-Lechani4 1IRIT/University of Toulouse, 2Paul Sabatier University - IRIT, 3Groupe Renault, 4IRIT

IntKB: A Verifiable Interactive Framework for Knowledge Base Completion Bernhard Kratzwald1, Guo Kunpeng2, Stefan Feuerriegel1, Dennis Diefenbach2 1ETH Zurich, 2University of Lyon

16:00 - 16:30    Session IND4 - INDUSTRY TRACK - Machine Learning Applications - Room Gràcia Chair: Vipul Raheja

An Industry Evaluation of Embedding-based Entity Alignment Ziheng Zhang, Hualuo Liu, Jiaoyan Chen, Xi Chen, Bo Liu, YueJia Xiang and Yefeng Zheng

Learning Domain Terms - Empirical Methods to Enhance Enterprise Text Analytics Performance Gargi Roy, Lipika Dey, Mohammad Shakir and Tirthankar Dasgupta

Model-agnostic Methods for Text Classification with Inherent Noise Kshitij Tayal, Rahul Ghosh and Vipin Kumar

ScopeIt: Scoping Task Relevant Sentences in Documents Barun Patra, Vishwas Suryanarayanan, Chala Fufa, Pamela Bhattacharya and Charles Lee

Uncertainty Modeling for Machine Comprehension Systems using Efficient Bayesian Neural Networks Zhengyuan Liu, Pavitra Krishnaswamy, Ai Ti Aw and Nancy Chen

Regularized Graph Convolutional Networks for Short Text Classification Kshitij Tayal, Nikhil Rao, Saurabh Agarwal, Xiaowei Jia, Karthik Subbian and Vipin Kumar

16:00 - 16:30    Session DEMO2 - Tools with higher purpose (Applications of NLP in other areas). Demos - Exhibition Room El Born Chair: Michal Ptaszynski

Session DEMO2 - A Multilingual Reading Comprehension System for more than 100 Languages. Anthony Ferritto, Sara Rosenthal, Mihaela Bornea, Kazi Hasan, Rishav Chakravarti, Salim Roukos, Radu-Florian and Avi Sil

BullStop: A Mobile App for Cyberbullying Prevention Semiu Salawu, Yulan He and Jo Lumsden

CogniVal in Action: An Interface for Customizable Cognitive Word Embedding Evaluation Nora Hollenstein, Adrian van der Lek and Ce Zhang

Demo Application for the AutoGOAL Framework Suilan Estevez-Velarde, Alejandro Piad-Morffis, Yoan Gutiérrez, Andres Montoyo, Rafael Muñoz-Guillena and Yudivián Almeida Cruz

Discussion Tracker: Supporting Teacher Learning about Students' Collaborative Argumentation in High School Classrooms Luca Lugini, Christopher Olshefski, Ravneet Singh, Diane Litman and Amanda Godley

Semantic search with domain-specific word-embedding and production monitoring in Fintech Mojtaba Farmanbar, Nikki Van Ommeren and Boyang Zhao

Ve'rdd. Narrowing the Gap between Paper Dictionaries, Low-Resource NLP and Community Involvement Khalid Alnajjar, Mika Hämäläinen, Jack Rueter and Niko Partanen

16:00 - 16:30    Session POSTER21 - Summarization. Posters - Exhibition Room Vila Olímpica

Reference and Document Aware Semantic Evaluation Methods for Korean Language Summarization Dongyub Lee1, Myeong Cheol Shin2, Taesun Whang3, Seungwoo Cho2, Byeongil Ko4, Daniel Lee4, EungGyun Kim2, Jaechoon Jo5 1Kakao Corp, 2Kakao Enterprise, 3Wisenut Inc., 4Kakao Enterprise Corp., 5Sangmyung University

At Which Level Should We Extract? An Empirical Analysis on Extractive Document Summarization Qingyu Zhou1, Furu Wei2, Ming Zhou3 1Harbin Institute of Technology, 2Microsoft Research, 3microsoft research asia

Fact-level Extractive Summarization with Hierarchical Graph Mask on BERT Ruifeng Yuan1, zili Wang2, Wenjie Li1 1The Hong Kong Polytechnic University, 2Xidian University

Flight of the PEGASUS? Comparing Transformers on Few-shot and Zero-shot Multi-document Abstractive Summarization Travis Goodwin1, Max Savery2, Dina Demner-Fushman3 1U.S. National Library of Medicine, 2NIH/NLM, 3National Library of Medicine

WSL-DS: Weakly Supervised Learning with Distant Supervision for Query Focused Multi-Document Abstractive Summarization Md Tahmid Rahman Laskar1, Enamul Hoque2, Jimmy Xiangji Huang3 1M.Sc. Student, York University, 2York University, 3School of Information Technology, York University

Multimodal Sentence Summarization via Multimodal Selective Encoding Haoran Li1, Junnan Zhu2, Jiajun Zhang3, Xiaodong He1, Chengqing Zong2 1JD AI Research, 2Institute of Automation, Chinese Academy of Sciences, 3Institute of Automation Chinese Academy of Sciences

Controllable Abstractive Sentence Summarization with Guiding Entities Changmeng Zheng1, Yi Cai1, Guanjie Zhang1, Qing Li2 1South China University of Technology, 2the Hong Kong Polytechnic University

HOLMS: Alternative Summary Evaluation with Large Language Models Yassine Mrabet1 and Dina Demner-Fushman2 1U.S. National Library of Medicine, 2National Library of Medicine

How Domain Terminology Affects Meeting Summarization Performance Jia Jin Koay, Alexander Roustai, Xiaojin Dai, Dillon Burns, Alec Kerrigan, Fei Liu University of Central Florida

An Anchor-Based Automatic Evaluation Metric for Document Summarization Kexiang Wang1, Tianyu Liu1, Baobao Chang2, Zhifang Sui1 1Peking University, 2Institute of Computational Linguistic, Peking University

Metrics also Disagree in the Low Scoring Range: Revisiting Summarization Evaluation Metrics Manik Bhandari, Pranav Narayan Gour, Atabak Ashfaq, Pengfei Liu Carnegie Mellon University

On the Faithfulness for E-commerce Product Summarization Peng Yuan1, Haoran Li1, Song Xu1, Youzheng Wu1, Xiaodong He1, Bowen Zhou2 1JD AI Research, 2JD.Com AI Research

SumTitles: a Summarization Dataset with Low Extractiveness Valentin Malykh1, Konstantin Chernis2, Ekaterina Artemova3, Irina Piontkovskaya2 1Huawei Noah's Ark Lab / Kazan Federal University, 2Huawei Noah's Ark Lab, 3NRU HSE

TWEETSUM: Event oriented Social Summarization Dataset Ruifang He, Liangliang Zhao, Huanyu Liu Tianjin University

16:30 - 17:00    Session LONG38 - Discourse 1 - Room El Raval Chair: Costanza Navarretta Co-Chair: Erik Ketzan

Exploiting a lexical resource for discourse connective disambiguation in German Peter Bourgonje1 and Manfred Stede2 1DFKI, 2University of Potsdam

Chinese Paragraph-level Discourse Parsing with Global Backward and Local Reverse Reading Feng Jiang, Xiaomin Chu, Peifeng Li, Fang Kong, Qiaoming Zhu Soochow University

A Neural Model for Aggregating Coreference Annotation in Crowdsourcing Maolin Li1, Hiroya Takamura2, Sophia Ananiadou1 1University of Manchester, 2The National Institute of Advanced Industrial Science and Technology (AIST)

Variation in Coreference Strategies across Genres and Production Media Berfin Aktaş and Manfred Stede University of Potsdam

Towards automatically generating Questions under Discussion to link information and discourse structure Kordula De Kuthy1, Madeeswaran Kannan2, Haemanth Santhi Ponnusamy2, Detmar Meurers3 1SFB 833, Universität Tübingen, 2University of Tübingen, 3Universität Tübingen

16:30 - 17:00    Session LONG39 - Classification systems - Room Montjuïc Chair: Goran Glavas Co-Chair: Xiao Zhang

Learning to Decouple Relations: Few-Shot Relation Classification with Entity-Guided Attention and Confusion-Aware Training Yingyao Wang1, Junwei Bao2, Guangyi Liu3, Youzheng Wu2, Xiaodong He2, Bowen Zhou4, Tiejun Zhao1 1Harbin Institute of Technology, 2JD AI Research, 3Chinese University of Hongkong, Shenzhen, 4JD.Com AI Research

Semi-supervised Multi-task Learning for Multi-label Fine-grained Sexism Classification Harika Abburi1, Pulkit Parikh1, Niyati Chhaya2, Vasudeva Varma1 1IIIT Hyderabad, 2Adobe Research

Using Eye-tracking Data to Predict the Readability of Brazilian Portuguese Sentences in Single-task, Multi-task and Sequential Transfer Learning Approaches Sidney Evaldo Leal1, João Marcos Munguba Vieira2, Erica dos Santos Rodrigues3, Elisângela Nogueira Teixeira2, Sandra Aluísio4 1University of Sao Paulo, Institute of Mathematics and Computer Sciences, 2Departamento de Letras Vernáculas - Universidade Federal do Ceará (UFC), 3Pontifícia Universidade Católica do Rio de Janeiro (PUC), Departamento de Letras, 4University of São Paulo

Retrieving Skills from Job Descriptions: A Language Model Based Extreme Multi-label Classification Framework Akshay Bhola1, Kishaloy Halder2, Animesh Prasad3, Min-Yen Kan4 1Indian Institute of Technology Kanpur, 2Zalando Research, 3Amazon Alexa, 4National University of Singapore

Native-like Expression Identification by Contrasting Native and Proficient Second Language Speakers Oleksandr Harust, Yugo Murawaki, Sadao Kurohashi Kyoto University

16:30 - 17:00    Session LONG40 - Resources and Datasets - Room Gràcia Chair: Fei Xia

An Analysis of Dataset Overlap on Winograd-Style Tasks Ali Emami1, Kaheer Suleman2, Adam Trischler2, Jackie Chi Kit Cheung1 1McGill University, 2Microsoft Research Montreal

The Indigenous Languages Technology project at NRC Canada: An empowerment-oriented approach to developing language software Roland Kuhn1, Fineen Davis1, Alain Désilets1, Eric Joanis1, Anna Kazantseva1, Rebecca Knowles1, Patrick Littell1, Delaney Lothian1, Aidan Pine1, Caroline Running Wolf1, Eddie Santos1, Darlene Stewart1, Gilles Boulianne2, Vishwa Gupta2, Brian Maracle Owennatékha3, Akwiratékha’ Martin4, Christopher Cox5, Marie-Odile Junker5, Olivia Sammons5, Delasie Torkornoo5, Nathan Thanyehténhas Brinklow6, Sara Child7, Benoît Farley8, David Huggins-Daines9, Daisy Rosenblum10, Heather Souter11 1National Research Council of Canada, 2Centre de recherche informatique de Montréal, 3Onkwawenna Kentyohkwa, 4Kahnawà:ke, 5Carleton University, 6Queen's University, 7Sanyakola Foundation, 8Pirurvik Centre, 9Nuance Communications, 10University of British Columbia, 11Prairies to Woodlands Indigenous Language Revitalization Circle

Cross-Lingual Emotion Lexicon Induction using Representation Alignment in Low-Resource Settings Arun Ramachandran1 and Gerard de Melo2 1Microsoft, 2Hasso Plattner Institute, University of Potsdam

Don’t Patronize Me! An Annotated Dataset with Patronizing and Condescending Language towards Vulnerable Communities Carla Perez Almendros, Luis Espinosa Anke, Steven Schockaert Cardiff University

100,000 Podcasts: A Spoken English Document Corpus Ann Clifton1, Sravana Reddy1, Yongze Yu1, Aasish Pappu2, Rezvaneh Rezapour3, Hamed Bonab4, Maria Eskevich5, Gareth Jones6, Jussi Karlgren1, Ben Carterette1, Rosie Jones1 1Spotify, 2Spotify Research, 3University of Illinois at Urbana-Champaign, 4University of Massachusetts Amherst, 5CLARIN ERIC, 6Dublin City University

16:30 - 17:00    Session POSTER22 - Translation, Crosslingual and Multilingual Systems. Posters - Exhibition Room Vila Olímpica

A Contextual Alignment Enhanced Cross Graph Attention Network for Cross-lingual Entity Alignment Zhiwen Xie1, Runjie Zhu2, Kunsong Zhao1, Jin Liu1, Guangyou Zhou3, Jimmy Xiangji Huang4 1School of Computer Science, Wuhan University, 2York University, 3School of Computer Science, Central China Normal University, 4School of Information Technology, York University

PheMT: A Phenomenon-wise Dataset for Machine Translation Robustness on User-Generated Contents Ryo Fujii1, Masato Mita2, Kaori Abe3, Kazuaki Hanawa2, Makoto Morishita4, Jun Suzuki5, Kentaro Inui3 1Tohoku University, 2RIKEN AIP / Tohoku University, 3Tohoku University / Riken, 4NTT Communication Science Laboratories, 5Tohoku University / RIKEN Center for AIP

Detecting Non-literal Translations by Fine-tuning Cross-lingual Pre-trained Language Models Yuming Zhai1, Gabriel ILLOUZ2, Anne Vilnat3 1Beijing Foreign Studies University, 2Université Paris Sud, 3LIMSI et Université Paris-Saclay

WikiUMLS: Aligning UMLS to Wikipedia via Cross-lingual Neural Ranking Afshin Rahimi1, Timothy Baldwin2, Karin Verspoor2 1The University of Queensland, 2The University of Melbourne

The Transference Architecture for Automatic Post-Editing Santanu Pal1, Hongfei Xu1, Nico Herbig2, Sudip Kumar Naskar3, Antonio Krüger2, Josef van Genabith4 1Saarland University, 2German Research Center for Artificial Intelligence (DFKI), Saarland Informatics Campus, 3Jadavpur University, 4DFKI

Better Sign Language Translation with STMC-Transformer Kayo Yin1 and Jesse Read2 1Carnegie Mellon University, 2École Polytechnique

A Simple and Effective Approach to Robust Unsupervised Bilingual Dictionary Induction Yanyang Li1, Yingfeng Luo2, Ye Lin2, Quan Du2, Huizhen Wang2, Shujian Huang3, Tong Xiao2, Jingbo Zhu2 1City University of Hong Kong, 2Northeastern University, 3National Key Laboratory for Novel Software Technology, Nanjing University

Data Selection for Bilingual Lexicon Induction from Specialized Comparable Corpora Martin Laville1, Amir Hazem2, Emmanuel Morin2, Phillippe Langlais3 1Université de Nantes, 2LS2N UMR CNRS 6004, 3Université de Montréal

A Locally Linear Procedure for Word Translation Soham Dan1, Hagai Taitelbaum2, Jacob Goldberger3 1University of Pennsylvania, 2Google Research, 3Bar-Ilan University

Rethinking the Value of Transformer Components Wenxuan Wang1 and Zhaopeng Tu2 1The Chinese University of Hong Kong, 2Tencent AI Lab

The SADID Evaluation Datasets for Low-Resource Spoken Language Machine Translation of Arabic Dialects Wael Abid Stanford University

Combining Word Embeddings with Bilingual Orthography Embeddings for Bilingual Dictionary Induction Silvia Severini1, Viktor Hangya2, Alexander Fraser2, Hinrich Schütze3 1Ludwig-Maximilians-Universität, 2Ludwig-Maximilians-Universität München, 3Center for Information and Language Processing, University of Munich

Understanding Translationese in Multi-view Embedding Spaces Koel Dutta Chowdhury1, Cristina España-Bonet2, Josef van Genabith3 1Saarland University, 2University of Saarland | DFKI, 3DFKI

Building The First English-Brazilian Portuguese Corpus for Automatic Post-Editing Felipe Almeida Costa1, Thiago Castro Ferreira2, Adriana Pagano2, Wagner Meira2 1Federal University of Minas Gerais (UFMG), 2Federal University of Minas Gerais

Analysing cross-lingual transfer in lemmatisation for Indian languages Kumar Saurav1, Kumar Saunack1, Pushpak Bhattacharyya2 1IIT Bombay, 2Indian Institute of Technology Bombay and Patna

17:00 - 17:30    Session LONG41 - Discourse 2 - Room El Raval Chair: Nianwen Xue

Neural Automated Essay Scoring Incorporating Handcrafted Features Masaki Uto, Yikuan Xie, Maomi Ueno The University of Electro-Communications

A Straightforward Approach to Narratologically Grounded Character Identification Labiba Jahan1, Rahul Mittal1, W. Victor Yarlott1, Mark Finlayson2 1Florida International University, 2FIU

Fine-grained Information Status Classification Using Discourse Context-Aware BERT Yufang Hou IBM Research

Free the Plural: Unrestricted Split-Antecedent Anaphora Resolution Juntao Yu1, Nafise Sadat Moosavi2, Silviu Paun1, Massimo Poesio1 1Queen Mary University of London, 2UKP Lab, Technische Universität Darmstadt

How coherent are neural models of coherence? Leila Pishdad1, Federico Fancellu2, Ran Zhang3, Afsaneh Fazly4 1Samsung AI Centre, 2Samsung AI Research Canada, 3Samsung AI Center - Toronto, 4University of Toronto; Samsung AI Research

17:00 - 17:30    Session LONG42 - Text Classification - Room Montjuïc Chair: Jeff Mitchell

Fact vs. Opinion: the Role of Argumentation Features in News Classification Tariq Alhindi1, Smaranda Muresan1, Daniel Preotiuc-Pietro2 1Columbia University, 2Bloomberg LP

Generating Plausible Counterfactual Explanations for Deep Transformers in Financial Text Classification Linyi Yang1, Eoin Kenny2, Tin Lok James Ng3, Yi Yang4, Barry Smyth2, Ruihai Dong2 1UCD, 2Insight Centre, UCD, 3University of Wollongong, 4Hong Kong University of Science and Technology

Text Classification by Contrastive Learning and Cross-lingual Data Augmentation for Alzheimer’s Disease Detection Zhiqiang Guo1, Zhaoci Liu1, Zhenhua Ling1, Shijin Wang2, Lingjing Jin3, Yunxia Li3 1University of Science and Technology of China, 2iFLYTEK Research, 3Shanghai Tongji Hospital, Tongji University School of Medicine

Multilingual Epidemiological Text Classification: A Comparative Study Stephen Mutuvi1, Emanuela Boros2, Antoine Doucet2, Adam Jatowt3, Gaël Lejeune4, Moses Odeo5 1University of La Rochelle/Multimedia University of Kenya, 2University of La Rochelle, 3Kyoto University, 4STIH, Paris-Sorbonne, 5Multimedia University of Kenya

Pointing to Select: A Fast Pointer-LSTM for Long Text Classification Jinhua Du1, Yan Huang1, Karo Moilanen2 1Investments AI, AIG, 2AIG Investments

17:00 - 17:30    Session LONG43 - Applications 4 - Room Gràcia Chair: Lluis Padró Co-Chair: Diptesh Kanojia

Aspect-based Document Similarity for Research Papers Malte Ostendorff1, Terry Ruas2, Till Blume3, Bela Gipp4, Georg Rehm5 1German Research Center for Artificial Intelligence, 2University of Michigan - Dearborn, 3University of Kiel, 4University of Wuppertal, 5DFKI

Explainable and Sparse Representations of Academic Articles for Knowledge Exploration Keng-Te Liao1, Zhihong Shen2, Chiyuan Huang3, Chieh-Han Wu2, PoChun Chen1, Kuansan Wang2, Shou-de Lin1 1National Taiwan University, 2Microsoft Research, 3Microsoft

“What is on your mind?” Automated Scoring of Mindreading in Childhood and Early Adolescence Venelin Kovatchev, Phillip Smith, Mark Lee, Imogen Grumley Traynor, Irene Luque Aguilera, Rory Devine University of Birmingham

A Deep Metric Learning Method for Biomedical Passage Retrieval Andrés Rosso-Mateus1, Fabio A. González2, Manuel Montes-y-Gómez3 1Universidad Nacional de Colombia, PhD Candidate, 2Universidad Nacional de Colombia, 3Laboratorio de Tecnologías del Lenguaje INAOE

Hierarchical Text Segmentation for Medieval Manuscripts Amir Hazem1, Beatrice Daille2, Dominique Stutzmann3, Christopher Kermorvant4, Louis Chevalier3 1LS2N UMR CNRS 6004, 2Université de Nantes - LS2N, 3IRHT, 4Teklia

17:00 - 17:30    Session POSTER23 - Applications: Abusive language, bias, fake news and rumours detection. Posters - Exhibition Room Vila Olímpica

Are We Ready for this Disaster? Towards Location Mention Recognition from Crisis Tweets Reem Suwaileh1, Muhammad Imran2, Tamer Elsayed1, Hassan Sajjad2 1Qatar University, 2Qatar Computing Research Institute

Mining Crowdsourcing Problems from Discussion Forums of Workers Zahra Nouri, Henning Wachsmuth, Gregor Engels Paderborn University

AbuseAnalyzer: Abuse Detection, Severity and Target Prediction for Gab Posts Mohit Chandra1, Ashwin Pathak1, Eesha Dutta2, Paryul Jain2, Manish Gupta3, Manish Shrivastava2, Ponnurangam Kumaraguru4 1International Institute of Information Technology, Hyderabad, 2International Institute of Information Technology Hyderabad, 3Microsoft, 4IIIT Delhi

A Survey of Automatic Personality Detection from Texts Sanja Stajner and Seren Yenikent Symanto Research

Mama/Papa, Is this Text for Me? Rashedur Rahman1, Gwénolé Lecorvé1, Aline Étienne2, Delphine Battistelli2, Nicolas Béchet3, Jonathan Chevelu1 1Univ Rennes, CNRS, IRISA, 2Université Paris-Nanterre, CNRS, MoDyCo, 3Université Bretagne SUD - IRISA

Hierarchical Bi-Directional Self-Attention Networks for Paper Review Rating Recommendation Zhongfen Deng1, Hao Peng2, Congying Xia1, Jianxin Li2, Lifang He3, Philip Yu4 1University of Illinois at Chicago, 2Beihang University, 3Lehigh University, 4Universtiy of Illinois at Chicago

Context in Informational Bias Detection Esther van den Berg1 and Katja Markert2 1Leibniz ScienceCampus ‘Empirical Linguistics and Computational Language Modeling’, 2Heidelberg University

HateGAN: Adversarial Generative-Based Data Augmentation for Hate Speech Detection RUI CAO1 and Roy Ka-Wei Lee2 1Singapore Management University, 2Singapore University of Technology and Design

Evaluating Unsupervised Representation Learning for Detecting Stances of Fake News Maike Guderlei and Matthias Aßenmacher Ludwig-Maximilians-Universität

XHate-999: Analyzing and Detecting Abusive Language Across Domains and Languages Goran Glavaš1, Mladen Karan2, Ivan Vulić3 1University of Mannheim, 2University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, Croatia, 3University of Cambridge

Detect All Abuse! Toward Universal Abusive Language Detection Models Kunze Wang, Dong Lu, Caren Han, SIQU LONG, Josiah Poon University of Sydney

Modeling Evolution of Message Interaction for Rumor Resolution Lei Chen1, Zhongyu Wei1, Jing Li2, Baohua Zhou3, Qi ZHANG3, Xuanjing Huang3 1School of Data Science, Fudan University, 2Department of Computing, The Hong Kong Polytechnic University, 3Fudan University

17:30 - 18:00    Session LONG44 - Relation Extraction - Room El Raval Chair: Gabor Recski

Regularized Attentive Capsule Network for Overlapped Relation Extraction Tianyi Liu1, Xiangyu Lin2, Weijia Jia3, Mingliang Zhou4, Wei Zhao5 1Shanghai Jiao Tong University, 2University of Macau, 3BNU-UIC Joint AI Resrach Institute, Beijing Normal University (Zhuhai) & Shanghai Jiao Tong University, 4the School of Computer Science, Chongqing University, 174 Shazheng Street, Shapingba District, 5American University of Sharjah，Sharjah United Arab Emirates

Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction Haiyang Yu1, Ningyu Zhang1, Shumin Deng1, Hongbin Ye1, Wei Zhang2, Huajun Chen1 1Zhejiang University, 2Alibaba Group

Dual Supervision Framework for Relation Extraction with Distant Supervision and Human Annotation Woohwan Jung and Kyuseok Shim Seoul National University

Graph Convolution over Multiple Dependency Sub-graphs for Relation Extraction Angrosh Mandya1, Danushka Bollegala2, Frans Coenen1 1University of Liverpool, 2University of Liverpool/Amazon

Towards Accurate and Consistent Evaluation: A Dataset for Distantly-Supervised Relation Extraction Tong Zhu1, Haitao Wang1, Junjie Yu1, Xiabing Zhou1, Wenliang Chen1, Wei Zhang2, Min Zhang3 1Soochow University, 2Alibaba Group, 3Suda

17:30 - 18:00    Session LONG45 - Inference and Comprehension - Room Montjuïc Chair: Jean-Francois Beaumont Co-Chair: Jing Ma

Multi-choice Relational Reasoning for Machine Reading Comprehension Wuya Chen1, Xiaojun Quan2, Chunyu Kit3, Zhengcheng Min1, Jiahai Wang1 1Sun Yat-sen University, 2School of Data and Computer Science, Sun Yat-sen University, 3City University of Hong Kong

FASTMATCH: Accelerating the Inference of BERT-based Text Matching Shuai Pang1, Jianqiang Ma2, ZEYU YAN2, Yang Zhang3, Jianping Shen4 1PING AN INSURANCE (GROUP) COMPANY OF CHINA, 2Ping An Life, AI Department, 3AI Department, Pingan Life Insurance, 4Ping An Life

DT-QDC: A Dataset for Question Comprehension in Online Test Sijin Wu1, Yujiu Yang1, Nicholas Yung2, Zhengchen Shen3, Zeyang Lei4 1tsinghua.edu.cn, 2Bielcrystal Datalab, 3Institute for Network Sciences and Cyberspace, Tsinghua University, 4Baidu Inc.

Read and Reason with MuSeRC and RuCoS: Datasets for Machine Reading Comprehension for Russian Alena Fenogenova1, Vladislav Mikhailov2, Denis Shevelev1 1Sberbank, 2Sberbank, Higher School of Economics

Knowledge-Enhanced Natural Language Inference Based on Knowledge Graphs Zikang Wang, Linjing Li, Daniel Zeng Institute of Automation, Chinese Academy of Sciences

17:30 - 18:00    Session POSTER24 - Language Resources and Evaluation. Posters - Exhibition Room

NYTWIT: A Dataset of Novel Words in the New York Times Yuval Pinter1, Cassandra L. Jacobs2, Max Bittker3 1Georgia Institute of Technology, 2University of Wisconsin, Madison, 3School for Poetic Computation, NY

SOME: Reference-less Sub-Metrics Optimized for Manual Evaluations of Grammatical Error Correction Ryoma Yoshimura1, Masahiro Kaneko1, Tomoyuki Kajiwara2, Mamoru Komachi1 1Tokyo Metropolitan University, 2Osaka University

Continual Lifelong Learning in Natural Language Processing: A Survey Magdalena Biesialska, Katarzyna Biesialska, Marta R. Costa-jussà Universitat Politècnica de Catalunya

XED: A Multilingual Dataset for Sentiment Analysis and Emotion Detection Emily Öhman1, Marc Pàmies2, Kaisla Kajava1, Jörg Tiedemann1 1University of Helsinki, 2Linköping University

Human or Neural Translation? Shivendra Bhardwaj1, David Alfonso Hermelo1, Phillippe Langlais2, Gabriel Bernier-Colborne3, Cyril Goutte3, Michel Simard4 1RALI / University of Montreal, 2Université de Montréal, 3National Research Council Canada, 4NRC

Biomedical Concept Relatedness – A large EHR-based benchmark Claudia Schulz1, Josh Levy-Kramer2, Camille Van Assel2, Miklos Kepes2, Nils Hammerla3 1Argus Data Insights, 2Babylon Health, 3Twitter

Domain-Specific Sentiment Lexicons Induced from Labeled Documents SM Mazharul Islam1, Xin Dong2, Gerard de Melo3 1University of Texas at Arlington, 2Rutgers University, 3Hasso Plattner Institute, University of Potsdam

Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus Isaac Caswell1, Theresa Breiner2, Daan van Esch2, Ankur Bapna3 1Google Research, 2Google, 3Google AI

Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps Xanh Ho1, Anh-Khoa Duong Nguyen2, Saku Sugawara1, Akiko Aizawa1 1National Institute of Informatics, 2National Institute of Advanced Industrial Science and Technology

RoBERT – A Romanian BERT Model Mihai Masala, Stefan Ruseti, Mihai Dascalu University Politehnica of Bucharest

Exploring the Language of Data Gábor Bella, Linda Gremes, Fausto Giunchiglia University of Trento

DaN+: Danish Nested Named Entities and Lexical Normalization Barbara Plank, Kristian Nørgaard Jensen, Rob van der Goot IT University of Copenhagen

New Benchmark Corpus and Models for Fine-grained Event Classification: To BERT or not to BERT? Jakub Piskorski1, Jacek Haneczok2, Guillaume Jacquet3 1Polish Academy of Sciences, 2Erste Group IT, 3Joint Research Centre - European Commission

A Geometry-Inspired Attack for Generating Natural Language Adversarial Examples Zhao Meng and Roger Wattenhofer ETH Zurich

Expert Concept-Modeling Ground Truth Construction for Word Embeddings Evaluation in Concept-Focused Domains Arianna Betti1, Martin Reynaert2, Thijs Ossenkoppele1, Yvette Oortwijn1, Andrew Salway3, Jelke Bloem1 1University of Amsterdam, 2ILLC - Universiteit van Amsterdam / DCA - Tilburg University, 3Uni Research

Creation of Corpus and analysis in Code-Mixed Kannada-English Twitter data for Emotion Prediction Abhinav Reddy Appidi, Vamshi Krishna Srirangam, Darsi Suhas, Manish Shrivastava International Institute of Information Technology, Hyderabad

18:00 - 18:30    Session PANEL2 - PANEL 2: On the generalization of NLP models – ways around data hunger. - Room El Raval Chair: Yue Zhang

Yue Zhang1, Xiaodan Zhu2, Jacob Andreas3, Nathanael Schärli4 1Westlake University, 2Queens University, Canada, 3MIT, 4Google

18:00 - 18:30    Session SHORT5 - Discourse, Parsing, Dialogue and others. Short papers - Room Montjuïc Chair: David Vilares Co-Chair: Serena Villata

Resource Constrained Dialog Policy Learning Via Differentiable Inductive Logic Programming Zhenpeng Zhou1, Ahmad Beirami2, Paul Crook3, Pararth Shah1, Rajen Subba3, Alborz Geramifard2 1Facebook Assistant, 2Facebook AI, 3Facebook

Fair Evaluation in Concept Normalization: a Large-scale Comparative Analysis for BERT-based Models Elena Tutubalina1, Artur Kadurin1, Zulfat Miftahutdinov2 1Insilico Medicine, 2Kazan Federal University

A Sentence Cloze Dataset for Chinese Machine Reading Comprehension Yiming Cui1, Ting Liu1, Ziqing Yang2, Zhipeng Chen2, Wentao Ma2, Wanxiang Che1, Shijin Wang2, Guoping Hu2 1Harbin Institute of Technology, 2iFLYTEK Research

Improving Document-Level Sentiment Analysis with User and Product Context Chenyang Lyu1, Jennifer Foster1, Yvette Graham2 1Dublin City University, 2Trinity College Dublin

Multilingual Neural RST Discourse Parsing Zhengyuan Liu, Ke Shi, Nancy Chen Institute for Infocomm Research, A*STAR

Intrinsic Quality Assessment of Arguments Henning Wachsmuth and Till Werner Paderborn University

Tree Representations in Transition System for RST Parsing Jinfen Li and Lu Xiao Syracuse University

Incremental Neural Lexical Coherence Modeling Sungho Jeon and Michael Strube Heidelberg Institute for Theoretical Studies

Statistical Parsing of Tree Wrapping Grammars Tatiana Bladier1, Jakub Waszczuk2, Laura Kallmeyer2 1Heinrich Heine University of Düsseldorf, 2University of Duesseldorf

Out-of-Task Training for Dialog State Tracking Models Michael Heck1, Christian Geishauser2, Hsien-chin Lin1, Nurul Lubis1, Marco Moresi2, Carel van Niekerk1, Milica Gasic2 1Heinrich Heine University, 2Heinrich Heine University Duesseldorf

18:00 - 18:30    Session POSTER25 - Machine Learning and Language Modelling. Posters - Exhibition Room Vila Olímpica

German's Next Language Model Branden Chan1, Stefan Schweter2, Timo Möller1 1deepset, 2DBMDZ

Language Model Transformers as Evaluators for Open-domain Dialogues Rostislav Nedelchev1, Jens Lehmann2, Ricardo Usbeck3 1University of Bonn, 2University of Bonn and Fraunhofer IAIS, 3Fraunhofer IAIS

Embedding Dynamic Attributed Networks by Modeling the Evolution Processes Zenan Xu1, Zijing Ou1, Qinliang Su1, Jianxing Yu1, Xiaojun Quan2, ZhenKun Lin1 1Sun Yat-sen University, 2School of Data and Computer Science, Sun Yat-sen University

Learning distributed sentence vectors with bi-directional 3D convolutions Bin Liu1, Liang Wang1, Guosheng Yin2 1Southwestern University of Finance and Economics, 2University of Hong Kong

Don't Invite BERT to Drink a Bottle: Modeling the Interpretation of Metonymies Using BERT and Distributional Representations Paolo Pedinotti and Alessandro Lenci University of Pisa

Neural Unsupervised Domain Adaptation in NLP---A Survey Alan Ramponi1 and Barbara Plank2 1University of Trento; Fondazione the Microsoft Research – University of Trento Centre for Computational and Systems Biology, 2IT University of Copenhagen

Exploring the Value of Personalized Word Embeddings Charles Welch, Jonathan K. Kummerfeld, Verónica Pérez-Rosas, Rada Mihalcea University of Michigan

Do Neural Language Models Overcome Reporting Bias? Vered Shwartz1 and Yejin Choi2 1University of Washington / Allen Institute for AI (AI2), 2University of Washington

Interpretable Multi-headed Attention for Abstractive Summarization at Controllable Lengths Ritesh Sarkhel1, Moniba Keymanesh2, Arnab Nandi1, Srinivasan Parthasarathy1 1Ohio State University, 2The Ohio State University

Scale down Transformer by Grouping Features for a Lightweight Character-level Language Model Sungrae Park1, Geewook Kim2, JUNYEOP LEE3, Junbum Cha4, Ji-Hoon Kim1, Hwalsuk Lee5 1Clova AI Research, NAVER Corporation, 2NAVER, 3Upstage AI Research, 4Clova AI Research, NAVER Corp., 5Upstage AI Research, Upstage

Attention Word Embedding Shashank Sonkar, Andrew Waters, Richard Baraniuk Rice University

CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters Hicham El Boukkouri1, Olivier Ferret2, Thomas Lavergne3, Hiroshi Noji4, Pierre Zweigenbaum1, Jun'ichi Tsujii5 1LIMSI, CNRS, Université Paris-Saclay, 2CEA LIST, 3LIMSI/CNRS & Université Paris Sud, 4Artificial Intelligence Research Center, AIST, 5Aritificial Intelligence Research Centre at AIST

Autoregressive Reasoning over Chains of Facts with Transformers Ruben Cartuyvels, Graham Spinks, Marie-Francine Moens Catholic University of Leuven

Augmenting NLP models using Latent Feature Interpolations Amit Jindal1, Arijit Ghosh Chowdhury1, Aniket Didolkar1, Di Jin2, Ramit Sawhney3, Rajiv Ratn Shah4 1Manipal Institute of Technology, 2MIT, 3Netaji Subhas Institute of Technology, 4IIIT Delhi

Neural Language Modeling for Named Entity Recognition Zhihong Lei1, Weiyue Wang2, Christian Dugast3, Hermann Ney2 1Apple Inc., 2RWTH Aachen University, 3RWTH, University of Aachen

18:30 - 19:00    Best Paper Awards and Closing - Room Poblenou