mlsanityData to 7 Oct 2026

What happens before and after: Multi-Event Commonsense in Event Coreference Resolution

arXiv 2302.09715 ↗First posted 20 Feb 2023cs.CLcited by 12

Not on the map. Why?

Abstract (arXiv)

Event coreference models cluster event mentions pertaining to the same real-world event. Recent models rely on contextualized representations to recognize coreference among lexically or contextually similar mentions. However, models typically fail to leverage commonsense inferences, which is particularly limiting for resolving lexically-divergent mentions. We propose a model that extends event mentions with temporal commonsense inferences. Given a complex sentence with multiple events, e.g., "The man killed his wife and got arrested", with the target event "arrested", our model generates plausible events that happen before the target event - such as "the police arrived", and after it, such as "he was sentenced". We show that incorporating such inferences into an existing event coreference model improves its performance, and we analyze the coreferences in which such temporal knowledge is required.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 30 of its 57 references that are in the map. First posted on arXiv 20 Feb 2023.

Builds on

30 of 57 references.

References · 30

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2020Longformer: The Long-Document Transformercited by 3,362
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  5. 2019COMET: Commonsense Transformers for Automatic Knowledge Graph Constructioncited by 450
  6. 2016A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Storiescited by 413
  7. 2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270
  8. 2020COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphscited by 254
  9. 2021Want To Reduce Labeling Cost? GPT-3 Can Helpcited by 196
  10. 2021Generating Datasets with Pretrained Language Modelscited by 192
  11. 2019Not Enough Data? Deep Learning to the Rescue!cited by 174
  12. 2020Data Augmentation using Pre-trained Transformer Modelscited by 168
18 more
  1. 2021Reframing Human-AI Collaboration for Generating Free-Text Explanationscited by 125
  2. 2020Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansionscited by 49
  3. 2019Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolutioncited by 43
  4. 2020DARE: Data Augmented Relation Extraction with GPT-2cited by 43
  5. 2021It's not Rocket Science : Interpreting Figurative Language in Narrativescited by 39
  6. 2020R3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledgecited by 32
  7. 2021Cross-document Coreference Resolution over Predicted Mentionscited by 29
  8. 2020Paragraph-level Commonsense Transformers with Recurrent Memorycited by 23
  9. 2017Event Coreference Resolution by Iteratively Unfolding Inter-dependencies among Eventscited by 19
  10. 2021Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreferencecited by 16
  11. 2020Paraphrasing vs Coreferring: Two Sides of the Same Coincited by 15
  12. 2021Realistic Evaluation Principles for Cross-document Coreference Resolutioncited by 15
  13. 2015A Hierarchical Distance-dependent Bayesian Model for Event Coreference Resolutioncited by 12
  14. 2021Sequential Cross-Document Coreference Resolutioncited by 12
  15. 2021A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference Resolutioncited by 11
  16. 2021Enhancing Interpretable Clauses Semantically using Pretrained Word Representationcited by 10
  17. 2021STaCK: Sentence Ordering with Temporal Commonsense Knowledgecited by 7
  18. 2022What GPT Knows About Who is Whocited by 7

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 7; 2025: 1.

12 papers.

  1. 2023ChatGPT Evaluation on Sentence Level Relations: A Focus on Temporal, Causal, and Discourse Relationscited by 39
  2. 2024Generating Harder Cross-document Event Coreference Resolution Datasets using Metaphoric Paraphrasingcited by 6
  3. 2024Any Other Thoughts, Hedgehog? Linking Deliberation Chains in Collaborative Dialoguescited by 6
  4. 2023Commonsense for Zero-Shot Natural Language Video Localizationcited by 4
  5. 2024Multimodal Cross-Document Event Coreference Resolution Using Linear Semantic Transfer and Mixed-Modality Ensemblescited by 4
  6. 2023Do large language models and humans have similar behaviors in causal inference with script knowledge?cited by 3
  7. 2024Synergetic Event Understanding: A Collaborative Approach to Cross-Document Event Coreference Resolution with Large Language Modelscited by 3
  8. 2023COMET-M: Reasoning about Multiple Events in Complex Sentencescited by 2
  9. 2024Okay, Let's Do This! Modeling Event Coreference with Generated Rationales and Knowledge Distillationcited by 2
  10. 2024Inferring Scientific Cross-Document Coreference and Hierarchy with Definition-Augmented Relational Reasoningcited by 2
  11. 2024EasyECR: A Library for Easy Implementation and Evaluation of Event Coreference Resolution Modelscited by 1
  12. 2025Argument-Centric Causal Intervention Method for Mitigating Bias in Cross-Document Event Coreference Resolutioncited by 0