Schedule

Talk session 1: Sentence-Level Semantics

8:30 - Compositional generalization with a broad-coverage semantic parser.
Pia Weißenhorn, Lucia Donatelli and Alexander Koller

8:40 - DRS Parsing as Sequence Labeling.
Minxing Shen and Kilian Evang

8:55 - Measuring Alignment Bias in Neural Seq2seq Semantic Parsers.
Davide Locatelli and Ariadna Quattoni

9:05 - Semantics-aware Attention Improves Neural Machine Translation.
Aviv Slobodkin, Leshem Choshen and Omri Abend

9:20 - Multilingual Extraction and Categorization of Lexical Collocations with Graph-aware Transformers.
Luis Espinosa Anke, Alexander Shvets, Alireza Mohammadshahi, James Henderson and Leo Wanner

9:35 - Comparison and Combination of Sentence Embeddings Derived from Different Supervision Signals.
Hayato Tsukagoshi, Ryohei Sasano and Koichi Takeda

Talk session 2: Evaluation

10:30 - Dyna-bAbI: unlocking bAbI's potential with dynamic synthetic benchmarking.
Ronen Tamari, Kyle Richardson, Noam Kahlon, Aviad Sar-Shalom, Nelson F. Liu, Reut Tsarfaty and Dafna Shahaf

10:45 - A Dynamic, Interpreted CheckList for Meaning-oriented NLG Metric Evaluation -- through the Lense of Semantic Similarity Rating.
Laura F. Zeidler, Juri Opitz and Anette Frank

11:00 - A Generative Approach for Mitigating Structural Biases in Natural Language Inference.
Dimion Asael, Zachary Ziegler and Yonatan Belinkov

11:15 - How Does Data Corruption Affect Natural Language Understanding Models? A Study on GLUE datasets.
Aarne Talman, Marianna Apidianaki, Stergios Chatzikyriakidis and Jörg Tiedemann

11:25 - AnaLog: Testing Analytical and Deductive Logic Learnability in Language Models.
Samuel Ryb, Mario Giulianelli, Arabella Sinclair and Raquel Fernández

11:40 - Unsupervised Reinforcement Adaptation for Class-Imbalanced Text Classification.
Yuexin Wu and Xiaolei Huang

Talk session 3: Lexical Semantics

3:30 - Distilling Hypernymy Relations from Language Models: On the Effectiveness of Zero-Shot Taxonomy Induction.
Devansh Jain and Luis Espinosa Anke

3:40 - PropBank Comes of Age---Larger, Smarter, and more Diverse.
Sameer Pradhan, Julia Bonn, Skatje Myers, Kathryn Conger, Tim O'Gorman, James Gung, Kristin Wright-Bettner and Martha Palmer

3:55 - Pretraining on Interactions for Learning Grounded Affordance Representations.
Jack Merullo, Dylan Ebert, Carsten Eickhoff and Ellie Pavlick

4:10 - Leveraging Three Types of Embeddings from Masked Language Models in Idiom Token Classification.
Ryosuke Takahashi, Ryohei Sasano and Koichi Takeda

4:20 - When Polysemy Matters: Modeling Semantic Categorization with Word Embeddings.
Elizabeth Soper and Jean-Pierre Koenig

4:30 - What Drives the Use of Metaphorical Language? Negative Insights from Abstractness, Affect, Discourse Coherence and Contextualized Word Representations.
Prisca Piccirilli and Sabine Schulte im Walde

4:40 - Assessing the Limits of the Distributional Hypothesis in Semantic Spaces: Trait-based Relational Knowledge and the Impact of Co-occurrences.
Mark Anderson and Jose Camacho-Collados

Talk session 4: Discourse and Dialog

8:30 - A Simple Unsupervised Approach for Coreference Resolution using Rule-based Weak Supervision.
Alessandro Stolfo, Chris Tanner, Vikram Gupta and Mrinmaya Sachan

8:40 - Online Coreference Resolution for Dialogue Processing: Improving Mention-Linking on Real-Time Conversations.
Liyan Xu and Jinho D. Choi

8:50 - DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models.
Gregor Betz and Kyle Richardson

9:05 - What do Large Language Models Learn about Scripts?
Abhilasha Sancheti and Rachel Rudinger

9:20 - "What makes a question inquisitive?" A Study on Type-Controlled Inquisitive Question Generation.
Lingyu Gao, Debanjan Ghosh and Kevin Gimpel

9:35 - Speech acts and Communicative Intentions for Urgency Detection.
Laurenti Enzo, Bourgon Nils, Farah Benamara, Mari Alda, Véronique Moriceau and Courgeon Camille

Talk session 5: Events

10:30 - Pairwise Representation Learning for Event Coreference.
Xiaodong Yu, Wenpeng Yin and Dan Roth

10:45 - Event Causality Identification via Generation of Important Context Words.
Hieu Man, Minh Van Nguyen and Thien Huu Nguyen

10:55 - Word-Label Alignment for Event Detection: A New Perspective via Optimal Transport.
Amir Pouran Ben Veyseh and Thien Huu Nguyen

11:05 - Capturing the Content of a Document through Complex Event Identification.
Zheng Qi, Elior Sulem, Haoyu Wang, Xiaodong Yu and Dan Roth

11:20 - Improved Induction of Narrative Chains via Cross-Document Relations.
Andrew Blair-Stanek and Benjamin Van Durme