*SEM 2020

The 9th Joint Conference on Lexical and Computational Semantics

December 12-13, 2020

Welcome

We are pleased to announce that SIGLEX, the Special Interest Group of the ACL, is organizing the 9th Joint Conference on Lexical and Computational Semantics. *SEM 2020 will be co-located with COLING 2020 and it will take place on the 12-13th of December 2020.

*SEM brings together researchers interested in the semantics of natural languages and its computational modeling. The conference embraces symbolic and probabilistic approaches, and everything in between; theoretical contributions as well as practical applications are welcome. The long-term goal of *SEM is to provide a stable forum for the growing number of NLP researchers working on all aspects of semantics.

Programme

Note: All times are in CET.

*SEM Day 1

14:00 - 14:10 Opening remarks

14:10 - 15:00 Session 1: Inference

Session Chair: Manaal Faruqui

14:10 - 14:28 Improving Medical NLI Using Context-Aware Domain Knowledge

Shaika Chowdhury, Philip S. Yu and Yuan Luo

14:28 - 14:41 Reading Comprehension as Natural Language Inference: A Semantic Analysis

Anshuman Mishra, Dhruvesh Patel, Aparna Vijayakumar, Xiang Li, Pavan Kapanipathi and Kartik Talamadupula

14:41- 15:00 Learning as Abduction: Trainable Natural Logic Theorem Prover for Natural Language Inference

Lasha Abzianidze

15:00 - 15:10 Break


15:10 - 15:54 Session 2: Cross-lingual Representations and Translation

Session Chair: Jose Camacho-Collados

15:10 - 15:23 Automatic Learning of Modality Exclusivity Norms with Crosslingual Word Embeddings

Emmanuele Chersoni, Rong Xiang, Qin Lu and Chu-Ren Huang

15:23 - 15:41 Joint Training for Learning Cross-lingual Embeddings with Sub-word Information without Parallel Corpora

Ali Hakimi Parizi and Paul Cook

15:41 - 15:54 Semantic Structural Decomposition for Neural Machine Translation

Elior Sulem, Omri Abend and Ari Rappoport

15:54 - 16:00 Break


16:00 - 17:00 *SEM & SemEval Keynote talk: Afra Alishahi (University of Tilburg)

Session Chair: Marianna Apidianaki

Title: Grounded language learning, from sounds and images to meaning

17:00 - 17:10 Break


17:10 - 17:59 Session 3: Sentiment, Morality and Inference

Session Chair: Emmanuele Chersoni

17:10 - 17:28 Token Sequence Labeling vs. Clause Classification for English Emotion Stimulus Detection

Laura Ana Maria Bostan and Roman Klinger

17:28 - 17:46 Knowledge Graphs meet Moral Values

Ioana Hulpuș, Jonathan Kobbe, Heiner Stuckenschmidt and Graeme Hirst

17:46 - 17:59 Natural Language Inference with Mixed Effects

William Gantt, Benjamin Kane and Aaron Steven White


*SEM Day 2


14:00 - 15:07 Session 4: Lexical Semantics

Session Chair: Ellie Pavlick

14:00 - 14:18 On the Systematicity of Probing Contextualized Word Representations: The Case of Hypernymy in BERT

Abhilasha Ravichander, Eduard Hovy, Kaheer Suleman, Adam Trischler and Jackie Chi Kit Cheung

14:18 - 14:36 Topology of Word Embeddings: Singularities Reflect Polysemy - Best Paper Award

Alexander Jakubowski, Milica Gasic and Marcus Zibrowius

14:36 - 14:54 Assessing Polyseme Sense Similarity through Co-predication Acceptability and Contextualised Embedding Distance

Janosch Haber and Massimo Poesio

14:54 - 15:07 Fine-tuning BERT with Focus Words for Explanation Regeneration

Isaiah Onando Mulang', Jennifer D'Souza and Sören Auer

15:07 - 15:15 Break


15:15 - 16:00 Session 5: Syntax, Semantics and Grounding

Session Chair: Marianna Apidianaki

15:15 - 15:28 PISA: A measure of Preference In Selection of Arguments to Model Verb Argument Recoverability

Giulia Cappelli and Alessandro Lenci

15:28 - 15:41 Learning Negation Scope from Syntactic Structure

Nick McKenna and Mark Steedman

15:41 - 16:00 A Visuospatial Dataset for Naturalistic Verb Learning

Dylan Ebert and Ellie Pavlick


16:00 - 17:00 *SEM Keynote talk: Luke Zettlemoyer (University of Washington and Facebook)

Session Chair: Manaal Faruqui

Title: De-noising Sequence-to-Sequence Pre-training

17:00 - 17:10 Break


17:10 - 18:04 Session 6: Dialog and Narration

Session Chair: Smaranda Muresan

17:10 - 17:28 Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking

Jianguo Zhang, Kazuma Hashimoto, Chien-Sheng Wu, Yao Wang, Philip Yu, Richard Socher and Caiming Xiong

17:28 - 17:46 "where is this relationship going?": Understanding Relationship Trajectories in Narrative Text

Keen You and Dan Goldwasser

17:46 - 18:04 Large Scale Author Obfuscation Using Siamese Variational Auto-Encoder: The SiamAO System

Chakaveh Saedi and Mark Dras