Conference Schedule - Thursday, April 22

Chair: Vera Demberg

Joint Coreference Resolution and Character Linking for Multiparty Conversation
Top-down Discourse Parsing via Sequence Labelling
Rethinking Coherence Modeling: Synthetic vs. Downstream Tasks

Chair: Barbara Plank

Identifying Named Entities as they are Typed
Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries
An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning

Chair: Roi Reichart

We Need To Talk About Random Splits
Building Representative Corpora from Illiterate Communities: A Review of Challenges and Mitigation Strategies for Developing Countries
Detecting Scenes in Fiction: A new Segmentation Task

Chair: Cristina España-Bonet

Multi-split Reversible Transformers Can Enhance Neural Machine Translation
Learning Coupled Policies for Simultaneous Machine Translation using Imitation Learning
Revisiting Multi-Domain Machine Translation (TACL)

Chair: Grzegorz Chrupala

ECOL-R: Encouraging Copying in Novel Object Captioning with Reinforcement Learning
An Empirical Study on the Generalization Power of Neural Representations Learned via Visual Guessing Games
Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCO

Chair: Sara Stymne

A phonetic model of non-native spoken word processing
Meta-Learning for Effective Multi-task and Multilingual Modelling
Deciphering Undersegmented Ancient Scripts Using Phonetic Prior (TACL)

Chair: Marianna Apidianaki

PolyLM: Learning about Polysemy through Language Modeling
Evaluating language models for the retrieval and categorization of lexical collocations
Unsupervised Word Polysemy Quantification with Multiresolution Grids of Contextual Embeddings

11:00-14:00

Gather Town

Chair: Matthew Purver

Zero-shot Generalization in Dialog State Tracking through Generative Question Answering
MIDAS: A Dialog Act Annotation Scheme for Open Domain HumanMachine Spoken Conversations
Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models

Chair: Anders Søgaard

Adaptive Mixed Component LDA for Low Resource Topic Modeling
Hidden Biases in Unreliable News Detection Datasets
ProFormer: Towards On-Device LSH Projection Based Transformers

Chair: Gosse Bouma

Disambiguatory Signals are Stronger in Word-initial Positions
Deep Subjecthood: Higher-Order Grammatical Features in Multilingual BERT
Probing for idiomaticity in vector space models

Chair: Jeremy Barnes

Learning From Revisions: Quality Assessment of Claims in Argumentation at Scale
"Laughing at you or with you": The Role of Sarcasm in Shaping the Disagreement Space
Challenges in Automated Debiasing for Toxic Language Detection

Chair: Ionut-Teodor Sorodoc

A Computational Analysis of Vagueness in Revisions of Instructional Texts
Familiar words but strange voices: Modelling the influence of speech variability on word recognition
Towards Personalised and Document-level Machine Translation of Dialogue
TMR: Evaluating NER Recall on Tough Mentions

If you’ve got it, flaunt it: Making the most of fine-grained sentiment annotations
ResPer: Computationally Modelling Resisting Strategies in Persuasive Conversations
CD^2CR: Co-reference resolution across documents and domains
Joint Coreference Resolution and Character Linking for Multiparty Conversation
Improving Factual Consistency Between a Response and Persona Facts
Top-down Discourse Parsing via Sequence Labelling
Ellipsis Resolution as Question Answering: An Evaluation
Mode Effects’ Challenge to Authorship Attribution
Automatic Data Acquisition for Event Coreference Resolution
An Expert Annotated Dataset for the Detection of Online Misogyny
Cross-Topic Rumor Detection using Topic-Mixtures
Learning From Revisions: Quality Assessment of Claims in Argumentation at Scale
What Sounds “Right” to Me? Experiential Factors in the Perception of Political Ideology
Us vs. Them: A Dataset of Populist Attitudes, News Bias and Emotions
“Laughing at you or with you”: The Role of Sarcasm in Shaping the Disagreement Space
Content-based Models of Quotation
Scientific Discourse Tagging for Evidence Extraction
From Toxicity in Online Comments to Incivility in American News: Proceed with Caution
BERTective: Language Models and Contextual Information for Deception Detection
Gender and Racial Fairness in Depression Research using Social Media
Challenges in Automated Debiasing for Toxic Language Detection
Rethinking Coherence Modeling: Synthetic vs. Downstream Tasks
Is the Understanding of Explicit Discourse Relations Required in Machine Reading Comprehension?

“Talk to me with left, right, and angles”: Lexical entrainment in spoken Hebrew dialogue
A Crowdsourced Open-Source Kazakh Speech Corpus and Initial Speech Recognition Baseline
Self-Training Pre-Trained Language Models for Zero- and Few-Shot Multi-Dialectal Arabic Sequence Labeling
Coordinate Constructions in English Enhanced Universal Dependencies: Analysis and Computational Modeling
Leveraging End-to-End ASR for Endangered Language Documentation: An Empirical Study on Yolóxochitl Mixtec
Data Augmentation for Voice-Assistant NLU using BERT-based Interchangeable Rephrase
Language Modelling as a Multi-Task Problem
On the evolution of syntactic information encoded by BERT’s contextualized representations
Calculating the optimal step of arc-eager parsing for non-projective trees
Subword Pooling Makes a Difference
VoiSeR: A New Benchmark for Voice-Based Search Refinement
On the Computational Modelling of Michif Verbal Morphology
On Hallucination and Predictive Uncertainty in Conditional Language Generation
Measuring and Improving Faithfulness of Attention in Neural Machine Translation
Segmenting Subtitles for Correcting ASR Segmentation Errors
PPT: Parsimonious Parser Transfer for Unsupervised Cross-Lingual Adaptation
DISK-CSV: Distilling Interpretable Semantic Knowledge with a Class Semantic Vector
Attention Can Reflect Syntactic Structure (If You Let It)
Are Neural Networks Extracting Linguistic Properties or Memorizing Training Data? An Observation with a Multilingual Probe for Predicting Tense
Interpretability for Morphological Inflection: from Character-level Predictions to Subword-level Rules
From characters to words: the turning point of BPE merges
WER-BERT: Automatic WER Estimation with BERT in a Balanced Ordinal Classification Paradigm

Unsupervised Sentence-embeddings by Manifold Approximation and Projection
BERxiT: Early Exiting for BERT with Better Fine-Tuning and Extension to Regression
Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning
How Fast can BERT Learn Simple Natural Language Inference?
Generative Text Modeling through Short Run Inference
Randomized Deep Structured Prediction for Discourse-Level Processing
Memorization vs. Generalization : Quantifying Data Leakage in NLP Performance Evaluation
BART-TL: Weakly-Supervised Topic Label Generation
Few-shot Learning for Slot Tagging with Attentive Relational Network
Active Learning for Sequence Tagging with Deep Pre-trained Models and {B}ayesian Uncertainty Estimates
Joint Energy-based Model Training for Better Calibrated Natural Language Understanding Models
Through the Looking Glass: Learning to Attribute Synthetic Text Generated by Language Models
Acquiring a Formality-Informed Lexical Resource for Style Analysis
ADePT: Auto-encoder based Differentially Private Text Transformation
Conceptual Grounding Constraints for Truly Robust Biomedical Name Representations
Annealing Knowledge Distillation
How Good (really) are Grammatical Error Correction Systems?
Extremely Small BERT Models from Mixed-Vocabulary Training
Diverse Adversaries for Mitigating Bias in Training
Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification
Text Augmentation in a Multi-Task View
Benchmarking a transformer-FREE model for ad-hoc retrieval

Unification-based Reconstruction of Multi-hop Explanations for Science Questions
Knowledge Base Question Answering through Recursive Hypergraphs
Identifying Named Entities as they are Typed
Cross-lingual Contextualized Topic Models with Zero-shot Learning
Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries
How Certain is Your {T}ransformer?
Learning Relatedness between Types with Prototypes for Relation Extraction
Probing into the Root: A Dataset for Reason Extraction of Structural Events from Financial Documents
FAST: Financial News and Tweet Based Time Aware Network for Stock Trading
Adaptive Mixed Component LDA for Low Resource Topic Modeling
Hidden Biases in Unreliable News Detection Datasets
LSOIE: A Large-Scale Dataset for Supervised Open Information Extraction
Progressively Pretrained Dense Corpus Index for Open-Domain Question Answering
Exploring the Limits of Few-Shot Link Prediction in Knowledge Graphs
ProFormer: Towards On-Device LSH Projection Based Transformers
ENPAR:Enhancing Entity and Entity Pair Representations for Joint Entity Relation Extraction
Representations for Question Answering from Documents with Tables and Text
Modeling Context in Answer Sentence Selection Systems on a Latency Budget
Do Multi-Hop Question Answering Systems Know How to Answer the Single-Hop Sub-Questions?
One-class Text Classification with Multi-modal Deep Support Vector Data Description
Regulatory Compliance through Doc2Doc Information Retrieval: A case study in EU/UK legislation where text similarity has limitations
An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning

Computationally Efficient Wasserstein Loss for Structured Labels
Ayato Toyokuni, Sho Yokoi, Hisashi Kashima and Makoto Yamada
Have Attention Heads in BERT Learned Constituency Grammar?
Ziyang Luo
Do we read what we hear? Modeling orthographic influences on spoken word recognition
Nicole Macher, Badr M. Abdullah, Harm Brouwer and Dietrich Klakow
PENELOPIE: Enabling Open Information Extraction for the Greek Language through Machine Translation
Dimitris Papadopoulos, Nikolaos Papadakis and Nikolaos Matsatsinis
A Computational Analysis of Vagueness in Revisions of Instructional Texts
Alok Debnath and Michael Roth
A reproduction of Apple's bi-directional LSTM models for language identification in short strings
Mads Toftrup, Søren Asger Sørensen, Manuel R. Ciosici and Ira Assent
Automatically Cataloging Scholarly Articles using Library of Congress Subject Headings
Nazmul Kazi, Nathaniel Lane and Indika Kahanda
Model Agnostic Answer Reranking System for Adversarial Question Answering
Sagnik Majumder, Chinmoy Samant and Greg Durrett
BERT meets Cranfield: Uncovering the Properties of Full Ranking on Fully Labeled Data
Negin Ghasemi and Djoerd Hiemstra
Siamese Neural Networks for Detecting Complementary Products
Marina Angelovska, Sina Sheikholeslami, Bas Dunn and Amir H. Payberah
Contrasting distinct structured views to learn sentence embeddings
Antoine Simoulin and Benoit Crabbé
Discrete Reasoning Templates for Natural Language Understanding
Hadeel Al-Negheimish, Pranava Madhyastha and Alessandra Russo
Multilingual Email Zoning
Bruno Jardim, Ricardo Rei and Mariana S. C. Almeida
Familiar words but strange voices: Modelling the influence of speech variability on word recognition
Alexandra Mayn, Badr M. Abdullah and Dietrich Klakow
Emoji-Based Transfer Learning for Sentiment Tasks
Susann Boy, Dana Ruiter and Dietrich Klakow
A Little Pretraining Goes a Long Way: A Case Study on Dependency Parsing Task for Low-resource Morphologically Rich Languages
Jivnesh Sandhan, Amrith Krishna, Ashim Gupta, Laxmidhar Behera and Pawan Goyal
TMR: Evaluating NER Recall on Tough Mentions
Jingxuan Tu and Constantine Lignos
The Effectiveness of Morphology-aware Segmentation in Low-Resource Neural Machine Translation
Jonne Saleva and Constantine Lignos
Making Use of Latent Space in Language GANs for Generating Diverse Text without Pre-training
Takeshi Kojima, Yusuke Iwasawa and Yutaka Matsuo
Beyond the English Web: Zero-Shot Cross-Lingual and Lightweight Monolingual Classification of Registers
Liina Repo, Valtteri Skantsi, Samuel Rönnqvist, Saara Hellström, Miika Oinonen, Anna Salmela, Douglas Biber, Jesse Egbert, Sampo Pyysalo and Veronika Laippala
Explaining and Improving BERT Performance on Lexical Semantic Change Detection
Severin Laicher, Sinan Kurtyigit, Dominik Schlechtweg, Jonas Kuhn and Sabine Schulte im Walde
Why Find the Right One?
Payal Khullar
Development of Conversational AI for Sleep Coaching Programme
Heereen Shim
Relating Relations: Meta-Relation Extraction from Online Health Forum Posts
Daniel Stickley
Towards Personalised and Document-level Machine Translation of Dialogue
Sebastian Vincent
Semantic-aware transformation of short texts using word embeddings: An application in the Food Computing domain
Andrea Morales-Garzón, Juan Gómez-Romero and Maria J. Martin-Bautista

A NEW SURPRISE MEASURE FOR EXTRACTING INTERESTING RELATIONSHIPS BETWEEN PERSONS
Hidetaka Kamigaito, Jingun Kwon, Young-In Song and Manabu Okumura
ANSWERQUEST: A SYSTEM FOR GENERATING QUESTION-ANSWER ITEMS FROM MULTI-PARAGRAPH DOCUMENTS
Melissa Roemmele, Deep Sidhpura, Steve DeNeefe and Ling Tsou
ASAD: ARABIC SOCIAL MEDIA ANALYTICS AND UNDERSTANDING
Sabit Hassan, Hamdy Mubarak, Ahmed Abdelali and Kareem Darwish
COVRELEX: A COVID-19 RETRIEVAL SYSTEM WITH RELATION EXTRACTION
Vu Tran, Van-Hien Tran, Phuong Nguyen, Chau Nguyen, Ken Satoh, Yuji Matsumoto and Minh Nguyen
CONVERSATIONAL AGENT FOR DAILY LIVING ASSESSMENT COACHING DEMO
Raymond Finzel, Aditya Gaydhani, Sheena Dufresne, Maria Gini and Serguei Pakhomov
DEBIE: A PLATFORM FOR IMPLICIT AND EXPLICIT DEBIASING OF WORD EMBEDDING SPACES
Niklas Friedrich, Anne Lauscher, Simone Paolo Ponzetto and Goran Glavaš
FORUM 4.0: AN OPEN-SOURCE USER COMMENT ANALYSIS FRAMEWORK
Marlo Haering, Jakob Smedegaard Andersen, Chris Biemann, Wiebke Loosen, Benjamin Milde, Tim Pietz, Christian Stöcker, Gregor Wiedemann, Olaf Zukunft and Walid Maalej
GRAPH MATCHING AND GRAPH REWRITING: GREW TOOLS FOR CORPUS EXPLORATION, MAINTENANCE AND CONVERSION
Bruno Guillaume
ELITR MULTILINGUAL LIVE SUBTITLING: DEMO AND STRATEGY
Ondřej Bojar, Dominik Macháček, Sangeet Sagar, Otakar Smrž, Jonáš Kratochvíl, Peter Polák, Ebrahim Ansari, Mohammad Mahmoudi, Rishu Kumar, Dario Franceschini, Chiara Canton, Ivan Simonini, Thai-Son Nguyen, Felix Schneider, Sebastian Stüker, Alex Waibel, Barry Haddow, Rico Sennrich and Philip Williams
FRAMEFORM: AN OPEN-SOURCE ANNOTATION INTERFACE FOR FRAMENET
Büşra Marşan and Olcay Taner Yıldız
GCM: A TOOLKIT FOR GENERATING SYNTHETIC CODE-MIXED TEXT
Mohd Sanad Zaki Rizvi, Anirudh Srinivasan, Tanuja Ganu, Monojit Choudhury and Sunayana Sitaram
PUNKTUATOR: A MULTILINGUAL PUNCTUATION RESTORATION SYSTEM FOR SPOKEN AND WRITTEN TEXT
Varnith Chordia
REPRESENTING ELMO EMBEDDINGS AS TWO-DIMENSIONAL TEXT ONLINE
Andrey Kutuzov and Elizaveta Kuzmenko
SLTEV: COMPREHENSIVE EVALUATION OF SPOKEN LANGUAGE TRANSLATION
Ebrahim Ansari, Ondřej Bojar, Barry Haddow and Mohammad Mahmoudi
SCOT: SENSE CLUSTERING OVER TIME: A TOOL FOR THE ANALYSIS OF LEXICAL CHANGE
Christian Haase, Saba Anwar, Seid Muhie Yimam, Alexander Friedrich and Chris Biemann
T2NER: TRANSFORMERS BASED TRANSFER LEARNING FRAMEWORK FOR NAMED ENTITY RECOGNITION
Saadullah Amin and Guenter Neumann
TRANKIT: A LIGHT-WEIGHT TRANSFORMER-BASED TOOLKIT FOR MULTILINGUAL NATURAL LANGUAGE PROCESSING
Minh Van Nguyen, Viet Dac Lai, Amir Pouran Ben Veyseh and Thien Huu Nguyen
USING AND COMPARING RHETORICAL STRUCTURE THEORY PARSERS WITH RST-WORKBENCH
Arne Neumann
WHICH IS BETTER FOR DEEP LEARNING: PYTHON OR MATLAB? ANSWERING COMPARATIVE QUESTIONS IN NATURAL LANGUAGE
Viktoriia Chekalina, Alexander Bondarenko, Chris Biemann, Meriem Beloucif, Varvara Logacheva and Alexander Panchenko

17:00-18:00

Keynote 2: Fernanda Ferreira

18:00-22:00

Gather Town