Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Okay, Let's Do This! Modeling Event Coreference with Generated Rationales and Knowledge Distillation (2404.03196v1)

Published 4 Apr 2024 in cs.CL

Abstract: In NLP, Event Coreference Resolution (ECR) is the task of connecting event clusters that refer to the same underlying real-life event, usually via neural systems. In this work, we investigate using abductive free-text rationales (FTRs) generated by modern autoregressive LLMs as distant supervision of smaller student models for cross-document coreference (CDCR) of events. We implement novel rationale-oriented event clustering and knowledge distillation methods for event coreference scoring that leverage enriched information from the FTRs for improved CDCR without additional annotation or expensive document clustering. Our model using coreference specific knowledge distillation achieves SOTA B3 F1 on the ECB+ and GVC corpora and we establish a new baseline on the AIDA Phase 1 corpus. Our code can be found at https://github.com/csu-signal/llama_cdcr

Definition Search Book Streamline Icon: https://streamlinehq.com
References (62)
  1. Linear cross-document event coreference resolution with x-amr. In Proceedings of the Joint Conference of the 15th Language Resources and Evaluation Conference, and, the 30th International Conference on Computational Linguistics, Torino, Italy. European Language Resources Association.
  2. X-amr annotation tool. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, Malta. Association for Computational Linguistics.
  3. 2*n2𝑛2*n2 * italic_n is better than n2superscript𝑛2n^{2}italic_n start_POSTSUPERSCRIPT 2 end_POSTSUPERSCRIPT: Decomposing event coreference resolution into two tractable problems. In Findings of the Association for Computational Linguistics: ACL 2023, pages 1569–1583, Toronto, Canada. Association for Computational Linguistics.
  4. Ben Alderson-Day and Charles Fernyhough. 2015. Inner speech: development, cognitive functions, phenomenology, and neurobiology. Psychological bulletin, 141(5):931.
  5. Amit Bagga and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In The first international conference on language resources and evaluation workshop on linguistics coreference, volume 1, pages 563–566. Citeseer.
  6. Longformer: The long-document transformer. arXiv e-prints, pages arXiv–2004.
  7. Barbara L Bershon. 1992. Cooperative problem solving: A link to inner speech. Interaction in cooperative groups. The theoretical anatomy of group learning, pages 36–48.
  8. Abductive commonsense reasoning. In International Conference on Learning Representations.
  9. Breaking the subtopic barrier in cross-document event coreference resolution. In Text2Story @ ECIR, pages 23–29.
  10. Generalizing Cross-Document Event Coreference Resolution Across Multiple Corpora. Computational Linguistics, 47(3):575–614.
  11. Generalizing cross-document event coreference resolution across multiple corpora. Computational Linguistics, 47(3):575–614.
  12. Cdlm: Cross-document language modeling. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2648–2662.
  13. Cross-document coreference resolution over predicted mentions. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 5100–5107.
  14. Prafulla Kumar Choubey and Ruihong Huang. 2017. Event coreference resolution by iteratively unfolding inter-dependencies among events. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2124–2133.
  15. What does bert look at? an analysis of bert’s attention. arXiv preprint arXiv:1906.04341.
  16. Andres Cremisini and Mark Finlayson. 2020. New insights into cross-document event coreference: Systematic comparison and a simplified approach. In Proceedings of the First Joint Workshop on Narrative Understanding, Storylines, and Events, pages 1–10, Online. Association for Computational Linguistics.
  17. Agata Cybulska and Piek Vossen. 2014. Using a sledgehammer to crack a nut? lexical diversity and event coreference resolution. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), pages 4545–4552.
  18. Agata Cybulska and Piek Vossen. 2015. Translating granularity of event slots into features for event coreference resolution. In Proceedings of the The 3rd Workshop on EVENTS: Definition, Detection, Coreference, and Representation, pages 1–10, Denver, Colorado. Association for Computational Linguistics.
  19. Andrew S Gordon and Jerry R Hobbs. 2017. A formal theory of commonsense psychology: How people think people think. Cambridge University Press.
  20. Knowledge distillation: A survey. International Journal of Computer Vision, 129:1789–1819.
  21. Focus on what matters: Applying discourse coherence theory to cross document coreference. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1406–1417, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
  22. Large language models are reasoning teachers. arXiv preprint arXiv:2212.10071.
  23. Coreference resolution with ilp-based weighted abduction. In Proceedings of COLING 2012, pages 1291–1308.
  24. Tinybert: Distilling bert for natural language understanding.
  25. Resolving event coreference with supervised representation learning and clustering-oriented regularization. arXiv preprint arXiv:1805.10985.
  26. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
  27. Large language models are zero-shot reasoners.
  28. Klaus Krippendorff. 2011. Computing krippendorff’s alpha-reliability.
  29. Nghia T Le and Alan Ritter. 2023. Are large language models robust zero-shot coreference resolvers? arXiv e-prints, pages arXiv–2305.
  30. Joint entity and event coreference resolution across documents. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 489–500.
  31. Using automatically extracted minimum spans to disentangle coreference evaluation from boundary detection. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Florence, Italy. Association for Computational Linguistics.
  32. Nafise Sadat Moosavi and Michael Strube. 2016. Which coreference evaluation metric do you trust? a proposal for a link-based entity aware metric. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 632–642.
  33. ExpBERT: Representation engineering with natural language explanations. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2106–2113, Online. Association for Computational Linguistics.
  34. Wt5?! training text-to-text models to explain their predictions. arXiv preprint arXiv:2004.14546.
  35. Multimodal cross-document event coreference resolution using linear semantic transfer and mixed-modality ensembles. In Proceedings of the Joint Conference of the 15th Language Resources and Evaluation Conference, and, the 30th International Conference on Computational Linguistics, Torino, Italy. European Language Resources Association.
  36. Axomiyaberta: A phonologically-aware transformer model for assamese. In Findings of the Association for Computational Linguistics: ACL 2023, pages 11629–11646.
  37. Training language models to follow instructions with human feedback.
  38. Gabriele Paul. 1993. Approaches to abductive reasoning: an overview. Artificial intelligence review, 7(2):109–152.
  39. Altaf Rahman and Vincent Ng. 2009. Supervised models for coreference resolution. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 968–977, Singapore. Association for Computational Linguistics.
  40. Robust textual inference via learning and abductive reasoning. In AAAI, pages 1099–1105.
  41. Explain yourself! leveraging language models for commonsense reasoning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4932–4942.
  42. What happens before and after: Multi-event commonsense in event coreference resolution. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1700–1716.
  43. Distilling reasoning capabilities into smaller language models. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7059–7073, Toronto, Canada. Association for Computational Linguistics.
  44. Learning by distilling context.
  45. Aleksandr Sokolov. 2012. Inner speech and thought. Springer Science & Business Media.
  46. Investigating the benefits of free-form rationales. arXiv preprint arXiv:2206.11083.
  47. Llama 2: Open foundation and fine-tuned chat models.
  48. A study in contradiction: Data and annotation for aida focusing on informational conflict in russia-ukraine relations. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 1831–1838.
  49. Dense paraphrasing for textual enrichment. In Proceedings of the 15th International Conference on Computational Semantics, pages 39–49, Nancy, France. Association for Computational Linguistics.
  50. A model-theoretic coreference scoring scheme. In Sixth Message Understanding Conference (MUC-6): Proceedings of a Conference Held in Columbia, Maryland, November 6-8, 1995.
  51. Don’t annotate, but validate: A data-to-text method for capturing event data. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018).
  52. Neural text generation with unlikelihood training. arXiv preprint arXiv:1908.04319.
  53. Symbolic knowledge distillation: from general language models to commonsense models. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4602–4625, Seattle, United States. Association for Computational Linguistics.
  54. Reframing human-AI collaboration for generating free-text explanations. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 632–658, Seattle, United States. Association for Computational Linguistics.
  55. Measuring association between labels and free-text rationales. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10266–10284.
  56. Boosting the efficiency of first-order abductive reasoning using pre-estimated relatedness between predicates. International Journal of Machine Learning and Computing, 5(2):114–120.
  57. A hierarchical distance-dependent bayesian model for event coreference resolution. Transactions of the Association for Computational Linguistics, 3:517–528.
  58. What GPT knows about who is who. In Proceedings of the Third Workshop on Insights from Negative Results in NLP, pages 75–81, Dublin, Ireland. Association for Computational Linguistics.
  59. Pairwise representation learning for event coreference. In Proceedings of the 11th Joint Conference on Lexical and Computational Semantics, pages 69–78.
  60. Cross-document event coreference resolution: Instruct humans or instruct GPT? In Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL), pages 561–574, Singapore. Association for Computational Linguistics.
  61. Abductive commonsense reasoning exploiting mutually exclusive explanations. arXiv preprint arXiv:2305.14618.
  62. Texygen: A benchmarking platform for text generation models. In The 41st international ACM SIGIR conference on research & development in information retrieval, pages 1097–1100.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now