Conference Program

Proceedings Preview: https://preview.aclanthology.org/iwcs-25-ingestion/volumes/2025.iwcs-1/

Day 1 — September 22, 2025

• 08:30 – 09:15 | Level 0
  Registration

• 09:15 – 09:30 | Level -1
  Opening remarks

• 09:30 – 10:30 | Level -1
  Invited speaker: Oana-Maria Camburu - Thoughts You Can Trust? Evaluating the Faithfulness of Model-Generated Explanations and Their Effects on Human Performance

• 10:30 – 11:00 | Level 0
  Coffee break

• 11:00 – 12:30 | Level -1
  Main session 1 (semantic parsing, linguistic phenomena)

  • Neurosymbolic AI for Natural Language Inference in French: combining LLMs and theorem provers for semantic parsing and natural language reasoning (Maximos Skandalis, Lasha Abzianidze, Richard Moot, Christian Retoré, Simon Robillard)
  • Is neural semantic parsing good at ellipsis resolution, or isn’t it? (Xiao Zhang, Johan Bos)
  • Retrieval-Augmented Semantic Parsing: Improving Generalization with Lexical Knowledge (Xiao Zhang, Qianru Meng, Johan Bos)

• 12:30 – 14:00
  Lunch break

• 14:00 – 15:00 | Level -1
  Invited speaker: Denis Paperno - Compositionality, Intensionality and LLMs: The Case of the Personal Relations Task

• 15:00 – 16:30 | Level 0
  Coffee break

• 15:00 – 16:30 | Level 2
  Poster session 1a (LLMs)

  • Can Large Language Models Robustly Perform Natural Language Inference for Japanese Comparatives? (Yosuke Mikami, Daiki Matsuoka, Hitomi Yanaka)
  • LLMs Struggle with NLI for Perfect Aspect: A Cross-Linguistic Study in Chinese and Japanese (LU JIE, Du Jin, Hitomi Yanaka)
  • Assessing LLMs’ Understanding of Structural Contrasts in the Lexicon (Shuxu LI, Antoine Venant, Philippe Langlais, François Lareau)
  • The Difficult Case of Intended and Perceived Sarcasm: a Challenge for Humans and Large Language Models (Hyewon Jang, Diego Frassinelli)
  • On the Role of Linguistic Features in LLM Performance on Theory of Mind Tasks (Ekaterina Kozachenko, Gonçalo Guiomar, Karolina Stanczak)

• 15:00 – 16:30 | Level 3
  Poster session 1b (sociolinguistics, applied linguistics)

  • Extracting Behaviors from German Clinical Interviews in Support of Autism Spectrum Diagnosis (Margareta A. Kulcsar, Ian Paul Grant, Massimo Poesio)
  • Semantic Analysis Experiments for French Citizens’ Contribution: Combinations of Language Models and Community Detection Algorithms (Sami Guembour, Dominguès, Sabine Ploux)
  • Mapping Semantic Domains Across India’s Social Media: Networks, Geography, and Social Factors (Gunjan Anand, Jonathan Dunn)
  • FRIDA to the Rescue! Analyzing Synthetic Data Effectiveness in Object-Based Common Sense Reasoning for Disaster Response (Mollie Shichman, Claire Bonial, Austin Blodgett, Taylor Pellegrin, Francis Ferraro, Rachel Rudinger)

• 16:30 – 18:00 | Level -1
  Main session 2 (LLMs and compositionality, hybrid approaches)

  • Context Effects on the Interpretation of Complement Coercion: A Comparative Study with Language Models in Norwegian (Matteo Radaelli, Emmanuele Chersoni, Alessandro Lenci, Giosuè Baggio)
  • DisCoCLIP: A Distributional Compositional Tensor Network Encoder for Vision-Language Understanding (Kin Ian Lo, Hala Hawashin, Mina Abbaszadeh, Tilen Limback-Stokin, Hadi Wazni, Mehrnoosh Sadrzadeh) (non-archival)
  • Evaluating Compositional Generalisation in VLMs and Diffusion Models (Beth Pearson, Bilal Boulbarss, Michael Wray, Martha Lewis) (non-archival)

• 19:00 – 21:00 | ALEX Düsseldorf, Graf-Adolf-Platz 15, 40213 Düsseldorf
  Conference dinner

---

Day 2 — September 23, 2025

• 08:30 – 09:30 | Level 0
  Registration

• 09:30 – 10:30 | Level -1
  Invited speaker: Alexander Koller - Solving Complex Problems with Large Language Models

• 10:30 – 11:00 | Level 0
  Coffee break

• 11:00 – 12:30 | Level -1
  Main session 3 (language models and linguistic knowledge)

  • Disentangling lexical and grammatical information in word embeddings (Li Liu, François Lareau)
  • The Proper Treatment of Verbal Idioms in German Discourse Representation Structure Parsing (Kilian Evang, Rafael Ehren, Laura Kallmeyer)
  • SemToken: Semantic-Aware Tokenization for Efficient Long-Context Language Modeling (Dong Liu, Yanxuan Yu)

• 12:30 – 14:00
  Lunch break

• 14:00 – 15:00 | Level -1
  Main session 4 (semantics and cognition)

  • Which Model Mimics Human Mental Lexicon Better? A Comparative Study of Word Embedding and Generative Models (Huacheng Song, Zhaoxin Feng, Emmanuele Chersoni, Chu-Ren Huang)
  • Finding Answers to Questions: Bridging between Type-based and Computational Neuroscience Approaches (Staffan Larsson, Jonathan Ginzburg, Robin Cooper, Andy Lücking)

• 15:00 – 16:30 | Level 0
  Coffee break

• 15:00 – 16:30 | Level 2
  Poster session 2a (resources)

  • FAMWA: A new taxonomy for classifying word associations (which humans improve at but LLMs still struggle with) (Maria A. Rodriguez, Marie Candito, Richard Huyghe)
  • Advancing the Database of Cross-Linguistic Colexifications with New Workflows and Data (Annika Tjuka, Robert Forkel, Christoph Rzymski, Johann-Mattis List)
  • ding-01 :ARG0: An AMR Corpus for Spontaneous French Dialogue (Jeongwoo Kang, Maria Boritchev, Maximin Coavoux)
  • Computational Semantics Tools for Glue Semantics (Mark-Matthias Zymla, Mary Dalrymple, Agnieszka Patejuk)

• 15:00 – 16:30 | Level 3
  Poster session 2b (discourse and context)

  • A German WSC dataset comparing coreference resolution by humans and machines (Wiebke Petersen, Katharina Spalek)
  • ProPara-CRTS: Canonical Referent Tracking for Reliable Evaluation of Entity State Tracking in Process Narratives (Bingyang Ye, Timothy Obiso, Jingxuan Tu, James Pustejovsky)
  • Does discourse structure help action prediction? A look at Correction Triangles. (Kate Thompson, Akshay Chaturvedi, Nicholas Asher)
  • Learning to Refer: How Scene Complexity Affects Emergent Communication in Neural Agents (Dominik Künkele, Simon Dobnik)
  • A Graph Autoencoder Approach for Gesture Classification with Gesture AMR (Huma Jamil, Ibrahim Khebour, Kenneth Lai, James Pustejovsky, Nikhil Krishnaswamy)

• 16:30 – 17:30 | Level -1
  Main session 5 (situated interpretation)

  • Not Just Who or What: Modeling the Interaction of Linguistic and Annotator Variation in Hateful Word Interpretation (Sanne Hoeken, Özge Alacam, Dong Nguyen, Massimo Poesio, Sina Zarrieß)
  • A Model of Information State in Situated Multimodal Dialogue (Kenneth Lai, Lucia Donatelli, Richard Brutti, James Pustejovsky)

• 17:30 – 18:00 | Level -1
  Closing remarks

---

Day 3 — September 24, 2025

• 08:30 – 09:00 | Level 0
  Registration

• 09:00 – 18:00 | Level -1
  The Second International Workshop on Construction Grammars and Natural Language Processing (CxGs+NLP 2025)

• 09:00 – 18:00 | Level 2
  ISA-21, The 21st Joint ACL - ISO Workshop on Interoperable Semantic Annotation

• 09:00 – 18:00 | Level 3
  Bridges and Gaps between Formal and Computational Linguistics (BriGap2)

• 10:30 – 11:00 | Level 0
  Coffee break

• 15:30 – 16:00 | Level 0
  Coffee break