Free the Plural: Unrestricted Split-Antecedent Anaphora Resolution

What it is about

Most coreference systems give a mention one antecedent, so «John met Mary. They had a chat» cannot be resolved: they refers to two separately introduced entities. The paper builds the first model for this split-antecedent case in general, on ARRAU (news, dialogue, fiction, medical; 507 training anaphors), with gold anaphors and mentions given. A span-ranking scorer in the Lee et al. style picks 2–5 antecedents above a threshold. Because the data is sparse, the authors add auxiliary data: crowd-annotated Phrase Detectives examples (noisy but high recall), ARRAU's element-of bridging links, and ordinary single-antecedent coreference, trained by concatenation, pre-training or a gradually decreasing share (annealing). The best combination reaches 70% lenient F1 and resolves all antecedents of 43.6% of anaphors, 11 and 21 points above the baseline. The paper also recalls psycholinguistic preferences: after «Michael met Peter and Maria» they may include Michael, after «Michael watched Peter and Maria» it prefers the pair.

Ideas

• I1. Add a split-antecedent step for they/them/their when no plural cluster agrees in the window: take the two (or more) animate singular participants of one earlier frame — agent and recipient, agent and a with-oblique, or the conjoined subjects of consecutive frames — and form a group entity whose members are both. Symmetric verbs (meet, marry, quarrel, play with) license agent+partner; perception or action verbs (watch, see) prefer a conjoined object alone. Put it in coref/src/sieve.rs after pronoun, print the frame it came from, and measure they/them/their precision (now 50.5 / 67.3 / 68.6 on GUM test) and CoNLL F1 on GUM dev. GUM marks split antecedents (SplitAnte, which coref resolve currently removes), so a separate count of SplitAnte cases resolved is possible on dev.
• I2. The same group entity in the frame reader's own resolver (prag/src/frames.rs, Ctx): «The fox and the crow met. They talked.» should give the Say frame both as speakers, and «Who went home?» after «They went home» should answer with both names. Measure frame bench coref F1 and the course questions whose gold answer names two characters.
• I3. Element-of bridging («two supermarkets … one is very small») is the inverse relation and the same rule shape: a numeral or one/the other/both/each pointing into a plural entity. A small sieve that links one of them / the other / both to the plural group gives the member reading; count these forms on GUM dev before building it.

For Mova

35. Reference and coreference §3.5 (split antecedents and plurals), §9 and §10. Code: coref/src/sieve.rs, coref/src/mention.rs (coordination groups already exist), coref/src/corefud.rs (keep SplitAnte for scoring on dev), prag/src/frames.rs. Measures: per-pronoun precision for they/them/their, CoNLL F1 on GUM dev with gold and SLM trees, frame bench coref F1. ARRAU is LDC data and Phrase Detectives has its own licence — tests only, if at all.

Topics: Coreference resolution

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/2020.coling-main.538 · arXiv 2011.00245

@inproceedings{yu2020free,
  title = {{Free the Plural: Unrestricted Split-Antecedent Anaphora Resolution}},
  author = {Yu, Juntao and Moosavi, Nafise Sadat and Paun, Silviu and Poesio, Massimo},
  booktitle = {Proceedings of the 28th International Conference on Computational Linguistics},
  year = {2020},
  doi = {10.18653/v1/2020.coling-main.538},
  eprint = {2011.00245},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2020.coling-main.538}
}

References

42 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. 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 (Volume 1: Long Papers), pages 47–57, Baltimore, Maryland, June. Association for Computational Linguistics. find
2. 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 (Volume 1: Long Papers), pages 1405–1415, Beijing, China, July. Association for Computational Linguistics. find
3. 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 (Volume 1: Long Papers), pages 643–653, Berlin, Germany, August. Association for Computational Linguistics. find
4. Kevin Clark, Minh-Thang Luong, Urvashi Khandelwal, Christopher D. Manning, and Quoc V. Le. 2019. BAM! born-again multi-task networks for natural language understanding. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5931–5937, Florence, Italy, July. Association for Computational Linguistics. find
5. Ryan Cotterell and Kevin Duh. 2017. Low-resource named entity recognition with cross-lingual, character-level neural conditional random fields. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 91–96, Taipei, Taiwan, November. Asian Federation of Natural Language Processing. find
6. 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, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota, June. Association for Computational Linguistics. find
7. Carola Eschenbach, Christopher Habel, Michael Herweg, and Klaus Rehkämper. 1989. Remarks on plural anaphora. In Proceedings of the fourth conference on European chapter of the Association for Computational Linguistics, pages 161–167. Association for Computational Linguistics. find
8. Yufang Hou. 2020. Bridging anaphora resolution as question answering. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1428–1438, Online, July. Association for Computational Linguistics. find our card
9. Mandar Joshi, Omer Levy, Luke Zettlemoyer, and Daniel Weld. 2019. BERT for coreference resolution: Baselines and analysis. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5803– 5808, Hong Kong, China, November. Association for Computational Linguistics. find
10. Mandar Joshi, Danqi Chen, Yinhan Liu, Daniel S. Weld, Luke Zettlemoyer, and Omer Levy. 2020. SpanBERT: Improving pre-training by representing and predicting spans. Transactions of the Association for Computational Linguistics, 8:64–77. find
11. Hans Kamp and Uwe Reyle. 1993. From Discourse to Logic. D. Reidel, Dordrecht. find
12. Ben Kantor and Amir Globerson. 2019. Coreference resolution with entity equalization. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 673–677, Florence, Italy, July. Association for Computational Linguistics. find
13. Barbara Kaup, Stephanie Kelter, and Christopher Habel. 2002. Representing referents of plural expressions and resolving plural anaphors. Language and Cognitive Processes, 17(4):405–450. find
14. Vid Kocijan, Oana-Maria Camburu, Ana-Maria Cretu, Yordan Yordanov, Phil Blunsom, and Thomas Lukasiewicz. 2019. WikiCREM: A large unsupervised corpus for coreference resolution. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4303–4312, Hong Kong, China, November. Association for Computational Linguistics. find
15. Ekaterina Lapshinova-Koltunski, Christian Hardmeier, and Pauline Krielke. 2018. ParCorFull: a parallel corpus annotated with full coreference. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), pages 423–428, Miyazaki, Japan, May. European Language Resources Association (ELRA). Heeyoung. Lee, Angel. Chang, Yves. Peirsman, Nathaneal. Chambers, Mihai. Surdeanu, and Dan. find
16. Jurafsky. 2013. Deterministic coreference resolution based on entity-centric, precision-ranked rules. Computational Linguistics, 39(4):885–916. find our card
17. 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, pages 188–197, Copenhagen, Denmark, September. Association for Computational Linguistics. find our card
18. 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, Volume 2 (Short Papers), pages 687–692, New Orleans, Louisiana, June. Association for Computational Linguistics. find
19. Gregory L. Murphy. 1984. Establishing and accessing referents in discourse. Memory & Cognition, 12(5):489– 497. find
20. Nikole D. Patson. 2014. The processing of plural expressions. Language and Linguistics Compass, 8(8):319–329. find
21. Silviu Paun, Jon Chamberlain, Udo Kruschwitz, Juntao Yu, and Massimo Poesio. 2018. A probabilistic annotation model for crowdsourcing coreference. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1926–1937, Brussels, Belgium, October-November. Association for Computational Linguistics. find
22. Viktor Pekar, Juntao Yu, Mohab El-karef, and Bernd Bohnet. 2014. Exploring options for fast domain adaptation of dependency parsers. In Proceedings of the First Joint Workshop on Statistical Parsing of Morphologically Rich Languages and Syntactic Analysis of Non-Canonical Languages, pages 54–65, Dublin, Ireland, August. Dublin City University. find
23. Haoruo Peng, Daniel Khashabi, and Dan Roth. 2015. Solving hard coreference problems. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 809–819, Denver, Colorado, May–June. Association for Computational Linguistics. find
24. Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. GloVe: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1532–1543, Doha, Qatar, October. Association for Computational Linguistics. find
25. Matthew 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, Volume 1 (Long Papers), pages 2227–2237, New Orleans, Louisiana, June. Association for Computational Linguistics. find
26. Massimo Poesio and Ron Artstein. 2008. Anaphoric annotation in the ARRAU corpus. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08), Marrakech, Morocco, May. European Language Resources Association (ELRA). find
27. Massimo Poesio, Roland Stuckardt, and Yannick Versley. 2016. Anaphora Resolution: Algorithms, Resources and Applications. Springer, Berlin. find
28. Massimo Poesio, Jon Chamberlain, Silviu Paun, Juntao Yu, Alexandra Uma, and Udo Kruschwitz. 2019. A crowdsourced corpus of multiple judgments and disagreement on anaphoric interpretation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1778–1789, Minneapolis, Minnesota, June. Association for Computational Linguistics. find
29. Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Olga Uryupina, and Yuchen Zhang. 2012. CoNLL-2012 shared task: Modeling multilingual unrestricted coreference in OntoNotes. In Proceedings of the Sixteenth Conference on Computational Natural Language Learning (CoNLL 2012), Jeju, Korea. find our card
30. Altaf Rahman and Vincent Ng. 2012. Resolving complex cases of definite pronouns: The Winograd schema challenge. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 777–789, Jeju Island, Korea, July. Association for Computational Linguistics. find
31. Anthony J. Sanford and F. Lockhart. 1990. Description types and method of conjoining as factors influencing plural anaphora. Journal of Semantics, 7:365–378. find
32. Wee M. Soon, Daniel C. Y. Lim, and Hwee T. Ng. 2001. A machine learning approach to coreference resolution of noun phrases. Computational Linguistics, 27(4). find our card
33. Olga Uryupina, Ron Artstein, Antonella Bristot, Federica Cavicchio, Francesca Delogu, Kepa J. Rodriguez, and Massimo Poesio. 2020. Annotating a broad range of anaphoric phenomena, in a variety of genres: the ARRAU corpus. Journal of Natural Language Engineering. find
34. Hardik Vala, Andrew Piper, and Derek Ruths. 2016. The more antecedents, the merrier: Resolving multi-antecedent anaphors. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2287–2296, Berlin, Germany, August. Association for Computational Linguistics. find
35. Kellie Webster, Marta Recasens, Vera Axelrod, and Jason Baldridge. 2018. Mind the GAP: A balanced corpus of gendered ambiguous pronouns. Transactions of the Association for Computational Linguistics, 6:605–617. find our card
36. Sam Wiseman, Alexander M. Rush, Stuart 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 (Volume 1: Long Papers), pages 1416–1426, Beijing, China, July. Association for Computational Linguistics. find
37. Sam Wiseman, Alexander M. Rush, and Stuart M. Shieber. 2016. Learning global features for coreference resolution. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 994–1004, San Diego, California, June. Association for Computational Linguistics. find
38. Zhilin Yang, Ruslan Salakhutdinov, and William W Cohen. 2017. Transfer learning for sequence tagging with hierarchical recurrent networks. Proceedings of the ICLR. find
39. Juntao Yu and Bernd Bohnet. 2015. Exploring confidence-based self-training for multilingual dependency parsing in an under-resourced language scenario. In Proceedings of the Third International Conference on Dependency Linguistics (Depling 2015), pages 350–358, Uppsala, Sweden, August. Uppsala University, Uppsala, Sweden. find
40. Juntao Yu, Mohab Elkaref, and Bernd Bohnet. 2015. Domain adaptation for dependency parsing via self-training. In Proceedings of the 14th International Conference on Parsing Technologies, pages 1–10, Bilbao, Spain, July. Association for Computational Linguistics. find
41. Ethan Zhou and Jinho D. Choi. 2018. They exist! introducing plural mentions to coreference resolution and entity linking. In Proceedings of the 27th International Conference on Computational Linguistics, pages 24–34, Santa Fe, New Mexico, USA, August. Association for Computational Linguistics. find
42. Joey Tianyi Zhou, Hao Zhang, Di Jin, Hongyuan Zhu, Meng Fang, Rick Siow Mong Goh, and Kenneth Kwok. 2019. Dual adversarial neural transfer for low-resource named entity recognition. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3461–3471, Florence, Italy, July. Association for Computational Linguistics. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/yu-2020-free-plural-unrestricted-split-antecedent/