Elamur Research⌕
☰
home / papers / 2016 / The More Antecedents, the Merrier: Resolving Multi-Antecedent Anaphors

The More Antecedents, the Merrier: Resolving Multi-Antecedent Anaphors

Summary

Most coreference systems assume that an anaphor points back to at most one antecedent. This rules out common cases such as "they" referring jointly to two characters introduced separately. Vala, Piper and Ruths study these multi-antecedent anaphors, which they call m-anaphors. They redefine NP anaphor resolution so that each mention may link to a set of earlier mentions.

To support the task, they build an annotated English literary corpus from Pride and Prejudice and stories from the Scribner anthology. Their analysis shows that m-anaphors cannot be resolved by simply taking the two most recent mentions, and that standard surface features do a poor job of separating m-anaphors from 1-anaphors.

Their resolver handles gold m-anaphoric "they" and "them". It works in three steps:

  • A maximum entropy pairwise model judges which candidate antecedents can form a group.
  • Local agglomerative clustering builds candidate groups from those judgments.
  • An existing coreference system, supported by corpus knowledge, scores the resulting clusters.

The resolver beats several baselines. Combined with the Clark and Manning (2015) system, it lifts full coreference performance. The released data provides an early benchmark for a phenomenon that OntoNotes and ACE do not annotate.

Key points

  • Corpus: Pride and Prejudice (P&P, 121,440 words) and 36 pieces drawn from Scribner's contemporary short fiction anthology, annotated in brat. The scheme is a modified ACE scheme that allows multiple antecedents, and inter-annotator agreement was 86.5%.
  • Frequency: P&P contains 1,289 m-anaphors, of which 55.8% are pronouns. Across the corpus, 765 instances of they/them (about 27.9%) are m-anaphoric.
  • Antecedent counts: 79.3% of m-anaphors have two antecedents, 13.2% have three and 3.7% have four. Intervening mentions are common.
  • Main result: Adding the m-anaphor resolver to Clark and Manning (2015) gains 0.6 CoNLL F1. Pairing that system with an oracle m-anaphor resolver instead reaches 44.8, a gain of 6.7, which shows how much room for improvement remains.
  • Availability: Data and code are released at github.com/networkdynamics/manaphor-acl2016.

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

11 papers of our library cite it (of the 140673 whose bibliographies we read); 7 of them have a page here, 4 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/p16-1216

@inproceedings{vala2016more,
  title = {{The More Antecedents, the Merrier: Resolving Multi-Antecedent Anaphors}},
  author = {Vala, Hardik and Piper, Andrew and Ruths, Derek},
  booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2016},
  doi = {10.18653/v1/p16-1216},
  url = {https://doi.org/10.18653/v1/p16-1216}
}

References

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

  1. 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. find our card
  2. Srinivas Bangalore and Owen Rambow. 2000. Exploiting a probabilistic hierarchical model for generation. In Proceedings of the 18th conference on Computational linguistics-Volume 1, pages 42–48. Association for Computational Linguistics. find
  3. Eric Bengtson and Dan Roth. 2008. Understanding the value of features for coreference resolution. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 294–303. Association for Computational Linguistics. find our card
  4. Shane Bergsma and Dekang Lin. 2006. Bootstrapping path-based pronoun resolution. In Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics, pages 33–40. Association for Computational Linguistics. find our card
  5. Anders Björkelund and Richárd Farkas. 2012. Data-driven multilingual coreference resolution using resolver stacking. In Joint Conference on EMNLP and CoNLL-Shared Task, pages 49–55. Association for Computational Linguistics. find our card
  6. Anders Björkelund and Pierre Nugues. 2011. Exploring lexicalized features for coreference resolution. In Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task, pages 45–50. Association for Computational Linguistics. find
  7. Kevin Clark and Christopher D Manning. 2015. Entity-centric coreference resolution with model stacking. In Association of Computational Linguistics (ACL). find our card
  8. Michael Collins and Nigel Duffy. 2002. New ranking algorithms for parsing and tagging: Kernels over discrete structures, and the voted perceptron. In Proceedings of the 40th annual meeting on association for computational linguistics, pages 263–270. Association for Computational Linguistics. find
  9. Pascal Denis, Jason Baldridge, et al. 2007. Joint determination of anaphoricity and coreference resolution using integer programming. In HLT-NAACL, pages 236–243. Citeseer. find our card
  10. George R Doddington, Alexis Mitchell, Mark A Przybocki, Lance A Ramshaw, Stephanie Strassel, and Ralph M Weischedel. 2004. The automatic content extraction (ace) program-tasks, data, and evaluation. In LREC, volume 2, page 1. find our card
  11. Greg Durrett and Dan Klein. 2013. Easy victories and uphill battles in coreference resolution. In EMNLP, pages 1971–1982. find our card
  12. Jenny Rose Finkel, Trond Grenager, and Christopher Manning. 2005. Incorporating non-local information into information extraction systems by gibbs sampling. In Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, pages 363–370. Association for Computational Linguistic… find
  13. Lynette Hirschman. 1997. {MUC-7 Coreference Task Definition}. find our card
  14. Jerry R Hobbs. 1978. Resolving pronoun references. Lingua, 44(4):311–338. find our card
  15. Eduard Hovy, Mitchell Marcus, Martha Palmer, Lance Ramshaw, and Ralph Weischedel. 2006. Ontonotes: the 90% solution. In Proceedings of the human language technology conference of the NAACL, Companion Volume: Short Papers, pages 57–60. Association for Computational Linguistics. find
  16. Robert JP Ingria and David Stallard. 1989. A computational mechanism for pronominal reference. In Proceedings of the 27th annual meeting on Association for Computational Linguistics, pages 262–271. Association for Computational Linguistics. find
  17. Megumi Kameyama. 1997. Recognizing referential links: An information extraction perspective. In Proceedings of a Workshop on Operational Factors in Practical, Robust Anaphora Resolution for Unrestricted Texts, pages 46–53. Association for Computational Linguistics. find
  18. Niveda Krishnamoorthy, Girish Malkarnenkar, Raymond J Mooney, Kate Saenko, and Sergio Guadar-rama. 2013. Generating natural-language video descriptions using text-mined knowledge. In AAAI, volume 1, page 2. find
  19. Jonathan K Kummerfeld and Dan Klein. 2013. Error-driven analysis of challenges in coreference resolution. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 265–277. find our card
  20. Irene Langkilde and Kevin Knight. 1998. Generation that exploits corpus-based statistical knowledge. In Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics-Volume 1, pages 704–710. Association for Comp… find
  21. Heeyoung Lee, Yves Peirsman, Angel Chang, Nathanael Chambers, Mihai Surdeanu, and Dan Jurafsky. 2011. Stanford’s multi-pass sieve coreference resolution system at the conll-2011 shared task. In Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task, pages 28–… find our card
  22. Christopher D Manning, Mihai Surdeanu, John Bauer, Jenny Rose Finkel, Steven Bethard, and David Mc-Closky. 2014. The stanford corenlp natural language processing toolkit. In ACL (System Demonstrations), pages 55–60. find our card
  23. Michael Martone, Lex Williford, and Rosellen Brown. 1999. The Scribner Anthology of Contemporary Short Fiction: Fifty North American Stories Since 1970. Touchstone. find
  24. Ruslan Mitkov. 2014. Anaphora resolution. Routledge. find
  25. Alessandro Moschitti. 2006. Making tree kernels practical for natural language learning. In EACL, volume 113, page 24. find
  26. Vincent Ng and Claire Cardie. 2002a. Identifying anaphoric and non-anaphoric noun phrases to improve coreference resolution. In Proceedings of the 19th international conference on Computational linguistics-Volume 1, pages 1–7. Association for Computational Linguistics. find
  27. Vincent Ng and Claire Cardie. 2002b. Improving machine learning approaches to coreference resolution. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pages 104– 111. Association for Computational Linguistics. find our card
  28. Vincent Ng. 2008. Unsupervised models for coreference resolution. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 640–649. Association for Computational Linguistics. find our card
  29. Vincent Ng. 2010. Supervised noun phrase coreference research: The first fifteen years. In Proceedings of the 48th annual meeting of the association for computational linguistics, pages 1396–1411. Association for Computational Linguistics. find our card
  30. Haoruo Peng, Daniel Khashabi, and Dan Roth. 2015. Solving hard coreference problems. Urbana, 51:61801. find our card
  31. Marta Recasens, Matthew Can, and Daniel Jurafsky. 2013a. Same referent, different words: Unsupervised mining of opaque coreferent mentions. In HLT-NAACL, pages 897–906. find
  32. Marta Recasens, Marie-Catherine de Marneffe, and Christopher Potts. 2013b. The life and death of discourse entities: Identifying singleton mentions. In HLT-NAACL, pages 627–633. find
  33. Wee Meng Soon, Hwee Tou Ng, and Daniel Chung Yong Lim. 2001. A machine learning approach to coreference resolution of noun phrases. Computational linguistics, 27(4):521–544. find our card
  34. Pontus Stenetorp, Sampo Pyysalo, Goran Topić, Tomoko Ohta, Sophia Ananiadou, and Jun’ichi Tsujii. 2012. brat: a web-based tool for NLP-assisted text annotation. In Proceedings of the Demonstrations Session at EACL 2012, Avignon, France, April. Association for Computational Linguistics. find
  35. Veselin Stoyanov, Nathan Gilbert, Claire Cardie, and Ellen Riloff. 2009. Conundrums in noun phrase coreference resolution: Making sense of the state-of-the-art. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language… find our card
  36. Veselin Stoyanov, Claire Cardie, Nathan Gilbert, Ellen Riloff, David Buttler, and David Hysom. 2010. Reconcile: A coreference resolution research platform. find
  37. Hardik Vala, David Jurgens, Andrew Piper, and Derek Ruths. 2015. Mr. bennet, his coachman, and the archbishop walk into a bar but only one of them gets recognized: On the difficulty of detecting characters in literary texts. In Proceedings of the 2015 Conference on Empirical Methods in Natural Langu… find
  38. Kees Van Deemter and Rodger Kibble. 2000. On coreferring: Coreference in muc and related annotation schemes. Computational linguistics, 26(4):629– 637. find our card
  39. Sam Wiseman, Alexander M Rush, Stuart M Shieber, Jason Weston, Heather Pon-Barry, Stuart M Shieber, Nicholas Longenbaugh, Sam Wiseman, Stuart M Shieber, Elif Yamangil, et al. 2015. Learning anaphoricity and antecedent ranking features for coreference resolution. In Proceedings of the 53rd Annual Mee… find our card
  40. Marta Recasens and Eduard Hovy. 2009. A deeper look into features for coreference resolution. In Anaphora Processing and Applications, pages 29– 42. Springer. find

↑ back to top