Elamur Research⌕
☰
home / papers / 2024 / Linear Cross-document Event Coreference Resolution with X-AMR

Linear Cross-document Event Coreference Resolution with X-AMR

Summary

Resolving event coreference by comparing every pair of mentions scales quadratically. This becomes very costly with large corpora and especially with LLM prompting. The authors replace pairwise scoring with a compact symbolic representation called X-AMR, a cross-document extension of Abstract Meaning Representation. For each event mention, X-AMR stores:

  • a PropBank roleset
  • four core arguments: ARG-0, ARG-1, ARG-Loc and ARG-Time

Arguments are linked across documents through a knowledge base (Wikipedia), and synonymous predicates are grouped with VerbNet classes. A multi-hop algorithm then clusters mentions over these graphs in linear time. The method is also interpretable, since each decision can be traced to graph components.

The authors enriched the ECB+ corpus with human X-AMR annotations using a prodi.gy-based model-in-the-loop tool. They then had GPT-4 generate the same graphs in zero-shot and few-shot settings, guided by condensed annotation guidelines, and compared the results with human annotations. The provided excerpt omits the results section, so GPT-4's scores are not reported here. The work offers a cheaper and more transparent route to cross-document ECR and probes where current LLMs fall short at this task.

Key points

  • X-AMR design: each event is reduced to a roleset plus ARG-0, ARG-1, ARG-Loc and ARG-Time. Nested (eventive) ARG-1 values are allowed, e.g. sign.02 taking agree.01 as its ARG-1.
  • Annotation coverage: all ECB+ mentions received roleset IDs, and 5,287 of 6,833 mentions also received full X-AMR. Only the Dev split is completely annotated.
  • Annotation process and agreement: two linguistics students annotated, with an adjudicator resolving disagreements. Roleset ID inter-annotator agreement was 0.84 (Train), 0.91 (Dev) and 0.80 (Test), so Dev serves as the experimental benchmark.
  • Resources: PropBank (over 11,000 Frame Files), VerbNet and Wikipedia identifiers, the latter chosen because GPT handles them well. Code and annotations are at github.com/ahmeshaf/gpt_coref.
  • LLM evaluation: GPT-4 produced X-AMR graphs in zero-shot and few-shot setups. These were fed to the linear ECR algorithm and compared with gold-standard human graphs.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Topics: Coreference resolution · Semantic role labeling

Cited by

6 papers of our library cite it (of the 140673 whose bibliographies we read); 1 of them have a page here, 5 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. arXiv 2404.08656

@inproceedings{ahmed2024linear,
  title = {{Linear Cross-document Event Coreference Resolution with X-AMR}},
  author = {Ahmed, Shafiuddin Rehan and Baker, George Arthur and Judge, Evi and Reagan, Michael and Wright-Bettner, Kristin and Palmer, Martha and Martin, James H.},
  booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
  year = {2024},
  doi = {10.63317/2r4vo8v943yz},
  eprint = {2404.08656},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.63317/2r4vo8v943yz}
}

References

52 references, 21 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. We want to thank the reviewers of LREC-COLING 2024 who helped improve this paper. Part of this work was done during an internship of one of the authors at ExplosionAI GmbH. We would also like to thank Ákos Kádár, Matthew Hannibal, Nikhil Krishnaswamy, Elizabeth Spaulding, and the Boul-derNLP group f… find
  2. Bibliographical Resources Shafiuddin Rehan Ahmed, Jon Cai, Martha Palmer, and James H. Martin. 2024. X-AMR annotation tool. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, Shafiuddin Rehan Ahmed, Abhijnan Nath, Ja… find
  3. Shafiuddin Rehan Ahmed, Abhijnan Nath, Michael Regan, Adam Pollins, Nikhil Krishnaswamy, and James H. Martin. 2023b. How good is the model in model-in-the-loop event coreference resolution annotation? In Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII), pages 136–145, Toronto, Canad… find
  4. Amit Bagga and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In In The First International Conference on Language Resources and Evaluation Workshop on Linguistics Coreference, pages 563–566. find our card
  5. Laura Banarescu, Claire Bonial, Shu Cai, Madalina Georgescu, Kira Griffitt, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Martha Palmer, and Nathan Schneider. 2013. Abstract Meaning Representation for sembanking. In Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discou… find our card
  6. Cosmin Bejan and Sanda Harabagiu. 2010. Unsupervised event coreference resolution with rich linguistic features. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 1412–1422, Uppsala, Sweden. Association for Computational Linguistics. find our card
  7. Iz Beltagy, Matthew E. Peters, and Arman Cohan. 2020. Longformer: The long-document transformer. find
  8. Susan Windisch Brown, Julia Bonn, Ghazaleh Kazeminejad, Annie Zaenen, James Pustejovsky, and Martha Palmer. 2022. Semantic representations for nlp using verbnet and the generative lexicon. Frontiers in Artificial Intelligence, 5. find
  9. Susan Windisch Brown, Dmitriy Dligach, and Martha Palmer. 2011. VerbNet class assignment as a WSD task. In Proceedings of the Ninth International Conference on Computational Semantics (IWCS 2011). find
  10. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chri… find
  11. Agata Cybulska and Piek Vossen. 2013. Semantic relations between events and their time, locations and participants for event coreference resolution. In Proceedings of the International Conference Recent Advances in Natural Language Processing RANLP 2013, pages 156–163, Hissar, Bulgaria. INCOMA Ltd.… find our card
  12. Avi Caciularu, Arman Cohan, Iz Beltagy, Matthew Peters, Arie Cattan, and Ido Dagan. 2021. CDLM: Cross-document language modeling. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2648–2662, Punta Cana, Dominican Republic. Association for Computational Linguistics. find
  13. Donald Davidson. 1969. The Individuation of Events, pages 216–234. Springer Netherlands, Dordrecht. find
  14. Jon Cai, Shafiuddin Rehan Ahmed, Julia Bonn, Kristin Wright-Bettner, Martha Palmer, and James H. Martin. 2023. CAMRA: Copilot for AMR annotation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 381–388, Singapore. Association fo… find
  15. Arie Cattan, Alon Eirew, Gabriel Stanovsky, Mandar Joshi, and Ido Dagan. 2021. Cross-document coreference resolution over predicted mentions. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 5100– 5107, Online. Association for Computational Linguistics. find our card
  16. 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, Copenhagen, Denmark. Association for Computational Lingui… find our card
  17. Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Eric Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Sharan Narang, Gaurav Mishra, Adams Yu, Vincent Zhao, Yanping Huang, A… find
  18. 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, Reykjavik, Iceland. European Language Resources Associa… find our card
  19. Pascal Denis and Jason Baldridge. 2009. Global joint models for coreference resolution and named entity classification. Procesamiento del Lenguaje Natural. find
  20. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,… find
  21. Jeffrey Flanigan, Sam Thomson, Jaime Carbonell, Chris Dyer, and Noah A. Smith. 2014. A discriminative graph-based parser for the Abstract Meaning Representation. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1426–1436, Balti… find
  22. Nicola Guarino, Riccardo Baratella, and Giancarlo Guizzardi. 2022. Events, their names, and their synchronic structure. Applied ontology, 17(2):249–283. find
  23. William Held, Dan Iter, and Dan Jurafsky. 2021. 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… find our card
  24. Kian Kenyon-Dean, Jackie Chi Kit Cheung, and Doina Precup. 2018. Resolving event coreference with supervised representation learning and clustering-oriented regularization. preprint arXiv:1805.10985. 2016), pages 47–56, Austin, Texas. Association for Computational Linguistics. arXiv Takeshi Kojima,… find our card
  25. Sha Li, Heng Ji, and Jiawei Han. 2021. Document-level event argument extraction by conditional generation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 894–908, Online. Association for Computa… find our card
  26. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pre-training approach. find
  27. Lawrence Brian Lombard. 2019. Events: A metaphysical study. Routledge. find
  28. Xiaoqiang Luo. 2005. On coreference resolution performance metrics. In Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, HLT ’05, page 25–32, USA. Association for Computational Linguistics. find our card
  29. Xiaoqiang Luo, Sameer Pradhan, Marta Recasens, and Eduard Hovy. 2014. An extension of BLANC to system mentions. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 24–29, Baltimore, Maryland. Association for Computational Linguis… find
  30. Inbal Magar and Roy Schwartz. 2022. Data contamination: From memorization to exploitation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 157–165, Dublin, Ireland. Association for Computational Linguistics. find
  31. Nafise Sadat Moosavi, Leo Born, Massimo Poesio, and Michael Strube. 2019. 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, pages 4168–4178, Florence,… find our card
  32. Tim O’Gorman, Kristin Wright-Bettner, and Martha Palmer. 2016. Richer event description: Integrating event coreference with temporal, causal and bridging annotation. In Proceedings of the 2nd Workshop on Computing News Storylines (CNS OpenAI. 2023. Gpt-4 technical report. find our card
  33. Martha Palmer, Daniel Gildea, and Paul Kingsbury. 2005. The Proposition Bank: An annotated corpus of semantic roles. Computational Linguistics, 31(1):71–106. find our card
  34. Sameer Pradhan, Julia Bonn, Skatje Myers, Kathryn Conger, Tim O’gorman, James Gung, Kristin Wright-bettner, and Martha Palmer. 2022. PropBank comes of Age—Larger, smarter, and more diverse. In Proceedings of the 11th Joint Conference on Lexical and Computational Semantics, pages 278–288, Seattle, Wa… find our card
  35. Sameer Pradhan, Xiaoqiang Luo, Marta Recasens, Eduard Hovy, Vincent Ng, and Michael Strube. 2014. Scoring coreference partitions of predicted mentions: A reference implementation. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pag… find our card
  36. Alec Radford, Karthik Narasimhan, Tim Salimans, Ilya Sutskever, et al. 2018. Improving language understanding by generative pre-training. find
  37. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. 2019. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9. find
  38. Karin Kipper Schuler. 2005. VerbNet: A broad-coverage, comprehensive verb lexicon. University of Pennsylvania. find
  39. Zhiyi Song, Ann Bies, Justin Mott, Xuansong Li, Stephanie Strassel, and Christopher Caruso. 2018. Cross-document, cross-language event coreference annotation using event hoppers. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan… find our card
  40. Zhiyi Song, Ann Bies, Stephanie Strassel, Tom Riese, Justin Mott, Joe Ellis, Jonathan Wright, Seth Kulick, Neville Ryant, and Xiaoyi Ma. 2015. From light to rich ERE: Annotation of entities, relations, and events. In Proceedings of the The 3rd Workshop on EVENTS: Definition, Detection, Coreference,… find
  41. Elizabeth Spaulding, Kathryn Conger, Anatole Gershman, Mahir Morshed, Susan Windisch Brown, James Pustejovsky, Rosario Uceda-Sosa, Sijia Ge, and Martha Palmer. 2024. PropBank goes public: Incorporation into Wikidata. In Proceedings of The 18th Linguistic Annotation Workshop (LAW-XVIII), pages 166–17… find
  42. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288. find
  43. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc. find
  44. Marc Vilain, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proceedings of the 6th Conference on Message Understanding, MUC6 ’95, page 45–52, USA. Association for Computational Linguistics. find our card
  45. Xiaozhi Wang, Ziqi Wang, Xu Han, Wangyi Jiang, Rong Han, Zhiyuan Liu, Juanzi Li, Peng Li, Yankai Lin, and Jie Zhou. 2020. MAVEN: A Massive General Domain Event Detection Dataset. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1652–1671, Onlin… find our card
  46. Runxin Xu, Peiyi Wang, Tianyu Liu, Shuang Zeng, Baobao Chang, and Zhifang Sui. 2022. A two-stream AMR-enhanced model for document-level event argument extraction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Tech… find
  47. Xianjun Yang, Yujie Lu, and Linda Petzold. 2022a. Few-shot document-level event argument extraction. ArXiv, abs/2209.02203. find
  48. Xiaohan Yang, Eduardo Peynetti, Vasco Meerman, and Chris Tanner. 2022b. 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. find
  49. Zhisong Zhang, Emma Strubell, and Eduard Hovy. 2022. Transfer learning from semantic role labeling to event argument extraction with template-based slot querying. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 2627–2647, Abu Dhabi, United Arab Emirat… find
  50. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed Chi, Quoc V Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems, volume 35, pages 24824– 24837. Curran Associates, Inc. find our card
  51. Kristin Wright-Bettner, Martha Palmer, Guergana Savova, Piet de Groen, and Timothy Miller. 2019. Cross-document coreference: An approach to capturing coreference without context. In Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019), pages 1–1… find our card
  52. Zhaofeng Wu, Linlu Qiu, Alexis Ross, Ekin Akyürek, Boyuan Chen, Bailin Wang, Najoung Kim, Jacob Andreas, and Yoon Kim. 2023. Reasoning or reciting? exploring the capabilities and limitations of language models through counterfactual tasks. arXiv preprint arXiv:2307.02477. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/ahmed-2024-linear-cross-document-event-coreference/