Conference Schedule - Friday, April 23

Chair: Torsten Zesch

ParaSCI: A Large Scientific Paraphrase Dataset for Longer Paraphrase Generation
NLQuAD: A Non-Factoid Long Question Answering Data Set
Towards a Decomposable Metric for Explainable Evaluation of Text Generation from AMR

Chair: Sebastian Ruder

Keep Learning: Self-supervised Meta-learning for Learning from Inference
Maximal Multiverse Learning for Promoting Cross-Task Generalization of Fine-Tuned Language Models
AdapterFusion: Non-Destructive Task Composition for Transfer Learning

Chair: Kairit Sirts

Error Analysis and the Role of Morphology
Facilitating Terminology Translation with Target Lemma Annotations
Enhancing Sequence-to-Sequence Neural Lemmatization with External Resources

Chair: Viviana Patti

Exploiting Emojis for Abusive Language Detection
Is ``hot pizza” Positive or Negative? Mining Target-aware Sentiment Lexicons
End-to-End Argument Mining as Biaffine Dependency Parsing

Chair: Eneko Agirre

Non-Autoregressive Text Generation with Pre-trained Language Models
Incremental Beam Manipulation for Natural Language Generation
Enconter: Entity Constrained Progressive Sequence Generation via Insertion-based Transformer

Chair: Preslav Nakov

Query Generation for Multimodal Documents
Zero-shot Neural Passage Retrieval via Domain-targeted Synthetic Question Generation
Complex Question Answering on knowledge graphs using machine translation and multi-task learning

Chair: James Henderson

Few-Shot Semantic Parsing for New Predicates
Project-then-Transfer: Effective Two-stage Cross-lingual Transfer for Semantic Dependency Parsing
Comparing Knowledge-Intensive and Data-Intensive Models for English Resource Semantic Parsing (CL)

11:00-14:00

Gather Town

Chair: Yufang Hou

AREDSUM: Adaptive Redundancy-Aware Iterative Sentence Ranking for Extractive Document Summarization
Discourse-Aware Unsupervised Summarization for Long Scientific Documents
How to Evaluate a Summarizer: Study Design and Statistical Analysis for Manual Linguistic Quality Evaluation

Chair: Andreas Vlachos

Multi-facet Universal Schema
Identify, Align, and Integrate: Matching Knowledge Graphs to Commonsense Reasoning Tasks
Do Syntax Trees Help Pre-trained Transformers Extract Information?

Chair: Raquel Fernandez

Evaluating Neural Model Robustness for Machine Comprehension
Coloring the Black Box: What Synesthesia Tells Us about Character Embeddings
Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?

Chair: François Yvon

Enriching Non-Autoregressive Transformer with Syntactic and Semantic Structures for Neural Machine Translation
The Source-Target Domain Mismatch Problem in Machine Translation
Better Neural Machine Translation by Extracting Linguistic Information from BERT

Chair: Yves Scherrer

Bootstrapping Multilingual AMR with Contextual Word Alignments
Multilingual Neural Machine Translation with Deep Encoder and Multiple Shallow Decoders
Cross-Cultural Similarity Features for Cross-Lingual Transfer Learning of Pragmatically Motivated Tasks

The Gutenberg Dialogue Dataset
Non-Autoregressive Text Generation with Pre-trained Language Models
Evaluating the Evaluation of Diversity in Natural Language Generation
Discourse Understanding and Factual Consistency in Abstractive Summarization
MONAH: Multi-Modal Narratives for Humans to analyze conversations
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
Quantifying Appropriateness of Summarization Data for Curriculum Learning
Self-Supervised and Controlled Multi-Document Opinion Summarization
Few Shot Dialogue State Tracking using Meta-learning
Globalizing BERT-based Transformer Architectures for Long Document Summarization
Unsupervised Extractive Summarization using Pointwise Mutual Information
Incremental Beam Manipulation for Natural Language Generation
StructSum: Summarization via Structured Representations
Unsupervised Abstractive Summarization of Bengali Text Documents
Informative and Controllable Opinion Summarization
Entity-level Factual Consistency of Abstractive Text Summarization
Modelling Context Emotions using Multi-task Learning for Emotion Controlled Dialog Generation
Extractive Summarization Considering Discourse and Coreference Relations based on Heterogeneous Graph
Summarising Historical Text in Modern Languages
Enconter: Entity Constrained Progressive Sequence Generation via Insertion-based Transformer

Disambiguatory Signals are Stronger in Word-initial Positions
Telling BERT’s Full Story: from Local Attention to Global Aggregation
Frequency-Guided Word Substitutions for Detecting Textual Adversarial Examples
Syntactic Nuclei in Dependency Parsing – A Multilingual Exploration
Searching for Search Errors in Neural Morphological Inflection
Dependency parsing with structure preserving embeddings
Error Analysis and the Role of Morphology
Applying the Transformer to Character-level Transduction
Paraphrases do not explain word analogies
First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT
Evaluating Neural Model Robustness for Machine Comprehension
Deep Subjecthood: Higher-Order Grammatical Features in Multilingual BERT
Coloring the Black Box: What Synesthesia Tells Us about Character Embeddings
Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees
Enhancing Sequence-to-Sequence Neural Lemmatization with External Resources
Cognition-aware Cognate Detection
Reanalyzing the Most Probable Sentence Problem: A Case Study in Explicating the Role of Entropy in Algorithmic Complexity
Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?
Probing for idiomaticity in vector space models
BERTese: Learning to Speak to BERT
Supertagging the Long Tail with Tree-Structured Decoding of Complex Categories
Recursive Non-Autoregressive Graph-to-Graph Transformer for Dependency Parsing with Iterative Refinement

Effects of Pre- and Post-Processing on type-based Embeddings in Lexical Semantic Change Detection
Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference
PolyLM: Learning about Polysemy through Language Modeling
The Role of Syntactic Planning in Compositional Image Captioning
Cross-lingual Entity Alignment with Incidental Supervision
Multiple Tasks Integration: Tagging, Syntactic and Semantic Parsing as a Single Task
Exploring Transitivity in Neural NLI Models through Veridicality
SANDI: Story-and-Images Alignment
Data Augmentation for Hypernymy Detection
ECOL-R: Encouraging Copying in Novel Object Captioning with Reinforcement Learning
Few-Shot Semantic Parsing for New Predicates
Evaluating language models for the retrieval and categorization of lexical collocations
Semantic Parsing of Disfluent Speech
An Empirical Study on the Generalization Power of Neural Representations Learned via Visual Guessing Games
Project-then-Transfer: Effective Two-stage Cross-lingual Transfer for Semantic Dependency Parsing
Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCO
Co-evolution of language and agents in referential games
Is Supervised Syntactic Parsing Beneficial for Language Understanding Tasks? An Empirical Investigation
Unsupervised Word Polysemy Quantification with Multiresolution Grids of Contextual Embeddings
Removing Word-Level Spurious Alignment between Images and Pseudo-Captions in Unsupervised Image Captioning
Comparing Knowledge-Intensive and Data-Intensive Models for English Resource Semantic Parsing

Multi-split Reversible Transformers Can Enhance Neural Machine Translation
Bootstrapping Multilingual AMR with Contextual Word Alignments
Does Typological Blinding Impede Cross-Lingual Sharing?
Quality Estimation without Human-labeled Data
Exploring Supervised and Unsupervised Rewards in Machine Translation
El Volumen Louder Por Favor: Code-switching in Task-oriented Semantic Parsing
Enriching Non-Autoregressive Transformer with Syntactic and Semantic Structures for Neural Machine Translation
WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia
A phonetic model of non-native spoken word processing
The Source-Target Domain Mismatch Problem in Machine Translation
Multilingual Neural Machine Translation with Deep Encoder and Multiple Shallow Decoders
Multilingual and cross-lingual document classification: A meta-learning approach
Lexical Normalization for Code-switched Data and its Effect on POS Tagging
Cross-Cultural Similarity Features for Cross-Lingual Transfer Learning of Pragmatically Motivated Tasks
Learning Coupled Policies for Simultaneous Machine Translation using Imitation Learning
Better Neural Machine Translation by Extracting Linguistic Information from BERT
CDA: a Cost Efficient Content-based Multilingual Web Document Aligner
Facilitating Terminology Translation with Target Lemma Annotations
Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Models
Meta-Learning for Effective Multi-task and Multilingual Modelling
Revisiting Multi-Domain Machine Translation
Deciphering Undersegmented Ancient Scripts Using Phonetic Prior

Query Generation for Multimodal Documents
Combining Deep Generative Models and Multi-lingual Pretraining for Semi-supervised Document Classification
Multi-facet Universal Schema
A Neural Few-Shot Text Classification Reality Check
Zero-shot Neural Passage Retrieval via Domain-targeted Synthetic Question Generation
Detecting Extraneous Content in Podcasts
ChEMU-Ref: A Corpus for Modeling Anaphora Resolution in the Chemical Domain
Benchmarking Machine Reading Comprehension: A Psychological Perspective
BERT Prescriptions to Avoid Unwanted Headaches: A Comparison of Transformer Architectures for Adverse Drug Event Detection
Multilingual Entity and Relation Extraction Dataset and Model
Identify, Align, and Integrate: Matching Knowledge Graphs to Commonsense Reasoning Tasks
DOCENT: Learning Self-Supervised Entity Representations from Large Document Collections
Do Syntax Trees Help Pre-trained Transformers Extract Information?
Fine-Grained Event Trigger Detection
On-Device Text Representations Robust To Misspellings via Projections
Adapting Event Extractors to Medical Data: Bridging the Covariate Shift
Metric-Type Identification for Multi-Level Header Numerical Tables in Scientific Papers
Graph-based Fake News Detection using a Summarization Technique
A Simple Three-Step Approach for the Automatic Detection of Exaggerated Statements in Health Science News
Complex Question Answering on knowledge graphs using machine translation and multi-task learning
“Killing Me” Is Not a Spoiler: Spoiler Detection Model using Graph Neural Networks with Dependency Relation-Aware Attention Mechanism
GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognition
Two Training Strategies for Improving Relation Extraction over Universal Graph

Keep Learning: Self-supervised Meta-learning for Learning from Inference
Maximal Multiverse Learning for Promoting Cross-Task Generalization of Fine-Tuned Language Models
AREDSUM: Adaptive Redundancy-Aware Iterative Sentence Ranking for Extractive Document Summarization
Exploiting Emojis for Abusive Language Detection
A Systematic Review of Reproducibility Research in Natural Language Processing
ParaSCI: A Large Scientific Paraphrase Dataset for Longer Paraphrase Generation
AdapterFusion: Non-Destructive Task Composition for Transfer Learning
Is ``hot pizza” Positive or Negative? Mining Target-aware Sentiment Lexicons
End-to-End Argument Mining as Biaffine Dependency Parsing
Discourse-Aware Unsupervised Summarization for Long Scientific Documents
Joint Learning of Representations for Web-tables, Entities and Types using Graph Convolutional Network
NLQuAD: A Non-Factoid Long Question Answering Data Set
Towards a Decomposable Metric for Explainable Evaluation of Text Generation from AMR
We Need To Talk About Random Splits
How to Evaluate a Summarizer: Study Design and Statistical Analysis for Manual Linguistic Quality Evaluation
Building Representative Corpora from Illiterate Communities: A Reviewof Challenges and Mitigation Strategies for Developing Countries
Process-Level Representation of Scientific Protocols with Interactive Annotation
A Study of Automatic Metrics for the Evaluation of Natural Language Explanations
Adaptive Fusion Techniques for Multimodal Data
Detecting Scenes in Fiction: A new Segmentation Task
Disfluency Correction using Unsupervised and Semi-supervised Learning
Towards More Fine-grained and Reliable NLP Performance Prediction

17:00-18:00

Keynote 3: Melanie Mitchell

18:00

Closing