Elamur Research
☰
home / papers / 2020 / CorefQA: Coreference Resolution as Query-based Span Prediction

CorefQA: Coreference Resolution as Query-based Span Prediction

Written for the Research library (claude-opus-5-5) from the paper text. Original — aclanthology.org/2020.acl-main.622.pdf

Summary

Most end-to-end coreference systems first propose candidate spans and then score pairs of them. This design has two weaknesses. A mention dropped at the proposal step can never be recovered. Pairs are also compared only through top-layer span vectors, so the surrounding context is barely used. CorefQA treats the task as extractive question answering instead. For each candidate mention, the sentence around it becomes a query with the mention marked. A span-extraction module then searches the whole document for every span that refers to the same entity. The model is built on SpanBERT and handles long texts with overlapping windows. It also encodes speakers by adding their names to their utterances, replacing the usual same-speaker features. Because the input looks like QA data, the model can first be trained on Quoref and SQuAD. It reaches 83.1 F1 on CoNLL-2012 and 87.5 F1 on GAP, which beats the earlier best results by 3.5 and 2.5 points. The study shows that a reading-comprehension framing can recover missed mentions. It also lets plentiful QA corpora make up for coreference annotation, which is scarce and costly.

Key points

  • Results: 83.1 F1 (+3.5) on the CoNLL-2012 benchmark and 87.5 F1 (+2.5) on GAP. Code is released at github.com/ShannonAI/CorefQA.
  • The architecture has a mention proposal module and a mention linking module. Candidate mentions are marked with <mention> tags inside the query, and clusters are formed from the scores of both stages.
  • Ablation: swapping the QA-style linking module for the mention-pair scorer of Lee et al. (2018) lowers performance by 8.4 F1. Pre-training on SQuAD adds 0.3 F1, and pre-training on Quoref adds a further gain.
  • Putting speaker names into the input works better than binary speaker features, with the clearest gains on documents that have many speakers. Unlike the parallel QA-style work of Aralikatte et al. (2019), CorefQA does not need gold mentions at inference time.
  • Mention recall stays higher than in the c2f-coref + SpanBERT baseline as fewer spans per word are kept. This is because the linking stage can still find spans that the proposal stage missed.

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

Cited by

106 papers of our library cite it (of the 140673 whose bibliographies we read); 13 of them have a page here, 93 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2020.acl-main.622

@inproceedings{wu2020corefqa,
  title = {{CorefQA: Coreference Resolution as Query-based Span Prediction}},
  author = {Wu, Wei and Wang, Fei and Yuan, Arianna and Wu, Fei and Li, Jiwei},
  booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},
  year = {2020},
  doi = {10.18653/v1/2020.acl-main.622},
  url = {https://doi.org/10.18653/v1/2020.acl-main.622}
}

References

45 references, 31 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Rahul Aralikatte, Matthew Lamm, Daniel Hardt, and Anders Søgaard. 2019. Ellipsis and coreference resolution as question answering. CoRR, abs/1908.11141. ↗
  2. 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
  3. Anders Björkelund and Jonas Kuhn. 2014. Learning structured perceptrons for coreference resolution with latent antecedents and non-local features. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014, June 22-27, 2014, Baltimore, MD, USA, Volume 1: Long Papers, pages 47–57. find
  4. Kevin Clark and Christopher D. Manning. 2015. Entity-centric coreference resolution with model stacking. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL 2015, July 26-31, 2015, Beijing, China, Volume 1: Long Papers, pages 1405–1415. find our card
  5. Kevin Clark and Christopher D. Manning. 2016. Improving coreference resolution by learning entity-level distributed representations. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, August 7-12, 2016, Berlin, Germany, Volume 1: Long Papers. find our card
  6. Pradeep Dasigi, Nelson F. Liu, Ana Marasovic, Noah A. Smith, and Matt Gardner. 2019a. Quoref: A reading comprehension dataset with questions requiring coreferential reasoning. CoRR, abs/1908.05803. ↗ our card
  7. Pradeep Dasigi, Nelson F Liu, Ana Marasovic, Noah A Smith, and Matt Gardner. 2019b. Quoref: A reading comprehension dataset with questions requiring coreferential reasoning. arXiv preprint arXiv:1908.05803. ↗ our card
  8. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: pre-training of Greg Durrett and Dan Klein. 2013. Easy victories and uphill battles in coreference resolution. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, EMNLP 2013, 18-21 October 2013, Grand Hyatt Seattle, Seattle, Washington, USA, A meeting of SIGDAT, a Special Interest Group of the ACL, pages 1971–1982. find our card
  9. Ali Emami, Paul Trichelair, Adam Trischler, Kaheer Suleman, Hannes Schulz, and Jackie Chi Kit Cheung. 2019. The knowref coreference corpus: Removing gender and number cues for difficult pronominal anaphora resolution. In Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, pages 3952–3961. find our card
  10. Hany Hassan, Anthony Aue, Chang Chen, Vishal Chowdhary, Jonathan Clark, Christian Federmann, Xuedong Huang, Marcin Junczys-Dowmunt, William Lewis, Mu Li, et al. 2018. Achieving human parity on automatic chinese to english news translation. arXiv preprint arXiv:1803.05567. ↗ our card
  11. Luheng He, Mike Lewis, and Luke Zettlemoyer. 2015. Question-answer driven semantic role labeling: Using natural language to annotate natural language. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP 2015, Lisbon, Portugal, September 17-21, 2015, pages 643–653. find our card
  12. Yutai Hou, Yijia Liu, Wanxiang Che, and Ting Liu. 2018. Sequence-to-sequence data augmentation for dialogue language understanding. In Proceedings of the 27th International Conference on Computational Linguistics, COLING 2018, Santa Fe, New Mexico, USA, August 20-26, 2018, pages 1234–1245. find
  13. Mandar Joshi, Danqi Chen, Yinhan Liu, Daniel S. Weld, Luke Zettlemoyer, and Omer Levy. 2019a. Spanbert: Improving pre-training by representing and predicting spans. CoRR, abs/1907.10529. ↗ our card
  14. Mandar Joshi, Omer Levy, Daniel S. Weld, and Luke Zettlemoyer. 2019b. BERT for coreference resolution: Baselines and analysis. CoRR, abs/1908.09091. ↗ our card
  15. Ben Kantor and Amir Globerson. 2019. Coreference resolution with entity equalization. In Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, pages 673–677. find
  16. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings. find
  17. Sosuke Kobayashi. 2018. Contextual augmentation: Data augmentation by words with paradigmatic relations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT, New Orleans, Louisiana, USA, June 1-6, 2018, Volume 2 (Short Papers), pages 452–457. find our card
  18. Kenton Lee, Luheng He, Mike Lewis, and Luke Zettlemoyer. 2017. End-to-end neural coreference resolution. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, September 9-11, 2017, pages 188–197. find our card
  19. Kenton Lee, Luheng He, and Luke Zettlemoyer. 2018. Higher-order coreference resolution with coarse-to-fine inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT, New Orleans, Louisiana, USA, June 1-6, 2018, Volume 2 (Short Papers), pages 687–692. find our card
  20. Omer Levy, Minjoon Seo, Eunsol Choi, and Luke Zettlemoyer. 2017. Zero-shot relation extraction via reading comprehension. In Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), Vancouver, Canada, August 3-4, 2017, pages 333–342. find
  21. Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2015. A diversity-promoting objective function for neural conversation models. arXiv preprint arXiv:1510.03055. ↗ our card
  22. Jiwei Li, Michel Galley, Chris Brockett, Georgios P Spithourakis, Jianfeng Gao, and Bill Dolan. 2016. A persona-based neural conversation model. arXiv preprint arXiv:1603.06155. ↗ our card
  23. Xiaoya Li, Jingrong Feng, Yuxian Meng, Qinghong Han, Fei Wu, and Jiwei Li. 2019a. A unified mrc framework for named entity recognition. arXiv preprint arXiv:1910.11476. ↗ our card
  24. Xiaoya Li, Fan Yin, Zijun Sun, Xiayu Li, Arianna Yuan, Duo Chai, Mingxin Zhou, and Jiwei Li. 2019b. Entity-relation extraction as multi-turn question answering. In Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, pages 1340–1350. find
  25. Xiaoqiang Luo. 2005. On coreference resolution performance metrics. In HLT/EMNLP 2005, Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference, 6-8 October 2005, Vancouver, British Columbia, Canada, pages 25–32. find our card
  26. Pierre-Emmanuel Mazaré, Samuel Humeau, Martin Raison, and Antoine Bordes. 2018. Training millions of personalized dialogue agents. arXiv preprint arXiv:1809.01984. ↗
  27. Bryan McCann, Nitish Shirish Keskar, Caiming Xiong, and Richard Socher. 2018. The natural language decathlon: Multitask learning as question answering. CoRR, abs/1806.08730. ↗ our card
  28. Leora Morgenstern, Ernest Davis, and Charles L. Ortiz Jr. 2016. Planning, executing, and evaluating the winograd schema challenge. AI Magazine, 37(1):50–54. find
  29. Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, October 25-29, 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL, pages 1532–1543. find
  30. Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word representations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2018, New Orleans, Louisiana, USA, June 1-6, 2018, Volume 1 (Long Papers), pages 2227–2237. find
  31. Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Olga Uryupina, and Yuchen Zhang. 2012. Conll-2012 shared task: Modeling multilingual unrestricted coreference in ontonotes. In Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning - Proceedings of the Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes, EMNLP-CoNLL 2012, July 13, 2012, Jeju Island, Korea, pages 1–40. find our card
  32. Pranav Rajpurkar, Robin Jia, and Percy Liang. 2018. Know what you don’t know: Unanswerable questions for squad. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, July 15-20, 2018, Volume 2: Short Papers, pages 784–789. find our card
  33. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016a. Squad: 100, 000+ questions for machine comprehension of text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016, Austin, Texas, USA, November 1-4, 2016, pages 2383–2392. find our card
  34. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016b. Squad: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250. ↗ our card
  35. Alon Talmor and Jonathan Berant. 2019. Multiqa: An empirical investigation of generalization and transfer in reading comprehension. In Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, pages 4911–4921. find
  36. Joseph P. Turian, Lev-Arie Ratinov, and Yoshua Bengio. 2010. Word representations: A simple and general method for semi-supervised learning. In ACL 2010, Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, July 11-16, 2010, Uppsala, Sweden, pages 384–394. find our card
  37. NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), pages 629–634. find
  38. Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, and Kai-Wei Chang. 2018. Gender bias in coreference resolution: Evaluation and debiasing methods. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT, New Orleans, Louisiana, USA, June 1-6, 2018, Volume 2 (Short Papers), pages 15–20. find our card
  39. Marc B. Vilain, John D. Burger, John S. Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proceedings of the 6th Conference on Message Understanding, MUC 1995, Columbia, Maryland, USA, November 6-8, 1995, pages 45–52. find our card
  40. Kellie Webster, Marta Recasens, Vera Axelrod, and Jason Baldridge. 2018. Mind the GAP: A balanced corpus of gendered ambiguous pronouns. TACL, 6:605–617. find our card
  41. Sam Wiseman, Alexander M. Rush, and Stuart M. Shieber. 2016. Learning global features for coreference resolution. In NAACL HLT 2016, The 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego California, USA, June 12-17, 2016, pages 994–1004. find our card
  42. Sam Wiseman, Alexander M. Rush, Stuart M. Shieber, and Jason Weston. 2015. Learning anaphoricity and antecedent ranking features for coreference resolution. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL 2015, July 26-31, 2015, Beijing, China, Volume 1: Long Papers, pages 1416–1426. find our card
  43. Rui Zhang, Cı́cero Nogueira dos Santos, Michihiro Yasunaga, Bing Xiang, and Dragomir R. Radev. 2018a. Neural coreference resolution with deep biaffine attention by joint mention detection and mention clustering. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, July 15-20, 2018, Volume 2: Short Papers, pages 102–107. find
  44. Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, and Jason Weston. 2018b. Personalizing dialogue agents: I have a dog, do you have pets too? arXiv preprint arXiv:1801.07243. ↗ our card
  45. Jieyu Zhao, Tianlu Wang, Mark Yatskar, Ryan Cotterell, Vicente Ordonez, and Kai-Wei Chang. 2019. Gender bias in contextualized word embeddings. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, find our card