Elamur Research⌕
☰
home / papers / 2020 / A Cluster Ranking Model for Full Anaphora Resolution

A Cluster Ranking Model for Full Anaphora Resolution

Summary

Most coreference systems are built for the CONLL 2012 (ONTONOTES) benchmark. That corpus does not annotate singletons or several kinds of non-referring expressions, such as expletives, so these systems skip part of the full anaphora resolution task. Yu, Uma and Poesio train on the ARRAU-based CRAC 2018 Shared Task data and the crowdsourced Phrase Detectives (PD) corpus. Their single neural model jointly detects mentions, builds coreference chains including singletons, and flags non-referring markables such as expletives and predicative NPs.

The model does not rank candidate antecedent mentions. It attaches each mention directly to an entity cluster. Each cluster representation combines its members with attention weights, because the mention that introduces an entity usually carries more information than later short forms like pronouns. Separate classifiers handle singletons and non-referring cases.

The system achieves the best reported results on CRAC and PD and stays competitive on CONLL. It also shows that richer annotation improves the standard evaluation on non-singleton chains, which argues for annotating these phenomena in new corpora.

Key points

  • On CRAC with system mentions, the model reaches a CONLL score of 77.9%, which the authors call the first modern result in this setting. That is 5.8 points above the shared-task baseline of 72.1%, even though the baseline used gold mentions. Non-referring expression detection reaches an F1 of 76.3%.
  • On PD, the model beats the previous best system by up to 5.3 points.
  • Training with singleton and non-referring annotations improves scores on non-singleton chains by up to 1.4 points.
  • The model has 4.8M trainable parameters, compared with 9.6M for the full Lee et al. (2018) system. It uses BiLSTM span representations built from GloVe, BERT and character CNN embeddings, plus a cluster-size feature split into 8 buckets. Training on oracle clusters speeds it up considerably.
  • On CONLL, it matches the best system not fine-tuned on BERT (Kantor and Globerson, 2019). Code: github.com/juntaoy/dali-full-anaphora.

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

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

Cite

The paper itself, not this page. BibTeX from the library's record of the work. arXiv 1911.09532

@inproceedings{yu2020cluster,
  title = {{A Cluster Ranking Model for Full Anaphora Resolution}},
  author = {Yu, Juntao and Uma, Alexandra and Poesio, Massimo},
  booktitle = {Proceedings of the Twelfth Language Resources and Evaluation Conference},
  year = {2020},
  eprint = {1911.09532},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1911.09532}
}

References

46 references, 25 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Ariel, M. (1990). Accessing Noun-Phrase Antecedents. Croom Helm Linguistics Series. Routledge. find
  2. Bahdanau, D., Cho, K., and Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473. ↗ our card
  3. Bergsma, S. and Yarowsky, D. (2011). Nada: A robust system for non-referential pronoun detection. In Iris Hendrickx, et al., editors, Anaphora Processing and Applications, pages 12–23, Berlin, Heidelberg. Springer Berlin Heidelberg. find
  4. Bergsma, S., Lin, D., and Goebel, R. (2008). Distributional identification of non-referential pronouns. In Proceedings of ACL-08: HLT, pages 10–18, Columbus, Ohio, June. Association for Computational Linguistics. find
  5. Björkelund, A. and Kuhn, J. (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), volume 1, pages 47–57. find our card
  6. Boyd, A., Gegg-Harrison, W., and Byron, D. (2005). Identifying non-referential it: a machine learning approach incorporating linguistically motivated patterns. In In Proceedings of the ACL Workshop on Feature Selection for Machine Learning in NLP, pages 40–47, Ann Arbor. find
  7. Chen, H., Fan, Z., Lu, H., Yuille, A., and Rong, S. (2018). Preco: A large-scale dataset in preschool vocabulary for coreference resolution. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 172–181, Brussels, Belgium, October-November. Association for Computational Linguistics. find our card
  8. Clark, K. and Manning, C. D. (2015). Entity-centric coreference resolution with model stacking. In Association for Computational Linguistics (ACL). find our card
  9. Clark, K. and Manning, C. D. (2016a). Deep reinforcement learning for mention-ranking coreference models. In Empirical Methods on Natural Language Processing (EMNLP). find our card
  10. Clark, K. and Manning, C. D. (2016b). Improving coreference resolution by learning entity-level distributed representations. In Association for Computational Linguistics (ACL). find our card
  11. De Marneffe, M.-C., Recasens, M., and Potts, C. (2015). Modeling the lifespan of discourse entities with application to coreference resolution. J. Artif. Int. Res., 52(1):445–475, January. ↗
  12. Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. In NAACL. find
  13. Evans, R. (2001). Applying machine learning toward an automatic classification of it. Literary and linguistic computing, 16(1):45–58. ↗
  14. Fernandes, E. R., dos Santos, C. N., and Milidiú, R. L. (2014). Latent trees for coreference resolution. Computational Linguistics, 40(4):801–835, December. ↗ our card
  15. Guillou, L. and Hardmeier, C. (2016). Protest: A test suite for evaluating pronouns in machine translation. In Nicoletta Calzolari (Conference Chair), et al., editors, Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), Paris, France, may. European Language Resources Association (ELRA). find
  16. Hardmeier, C., Nakov, P., Stymne, S., Tiedemann, J., Versley, Y., and Cettolo, M. (2015). Pronoun-focused mt and cross-lingual pronoun prediction: Findings of the 2015 discomt shared task on pronoun translation. In Proceedings of the Second Workshop on Discourse in Machine Translation, pages 1–16, Lisbon, Portugal, September. Association for Computational Linguistics. find
  17. Joshi, M., Chen, D., Liu, Y., Weld, D. S., Zettlemoyer, L., and Levy, O. (2019a). Spanbert: Improving pre-training by representing and predicting spans. arXiv preprint arXiv:1907.10529. ↗ our card
  18. Joshi, M., Levy, O., Zettlemoyer, L., and Weld, D. (2019b). 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 our card
  19. Kantor, B. and Globerson, A. (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 our card
  20. Karttunen, L. (1976). Discourse referents. In Syntax and Semantics 7 - Notes from the Linguistic Underground. Academic Press. find
  21. Lappin, S. and Leass, H. J. (1994). An algorithm for pronominal anaphora resolution. Computational Linguistics, 20(4):535–562. ↗ our card
  22. Lee, H., Chang, A., Peirsman, Y., Chambers, N., Surdeanu, M., and Jurafsky, D. (2013). Deterministic coreference resolution based on entity-centric, precision-ranked rules. Computational Linguistics, 39(4):885–916. ↗ our card
  23. Lee, K., He, L., Lewis, M., and Zettlemoyer, L. (2017). End-to-end neural coreference resolution. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. find our card
  24. Lee, K., He, L., and Zettlemoyer, L. S. (2018). Higher-order coreference resolution with coarse-to-fine inference. In Proceedings of the 2018 Annual Conference of the North American Chapter of the Association for Computational Linguistics. find our card
  25. Loáiciga, S., Guillou, L., and Hardmeier, C. (2017). What is it? disambiguating the different readings of the pronoun ‘it’. In Proc. of EMNLP. find our card
  26. Luo, X., Ittycheriah, A., Jing, H., Kambhatla, N., and Roukos, S. (2004). A mention-synchronous coreference resolution algorithm based on the bell tree. In Proc. of the ACL. find our card
  27. Martschat, S. and Strube, M. (2015). Latent structures for coreference resolution. Transactions of the Association for Computational Linguistics, 3:405–418. ↗ our card
  28. Mitkov, R., Evans, R., and Orasan, C. (2002). A new, fully automatic version of Mitkov’s knowledge-poor pronoun resolution method. In International Conference on Intelligent Text Processing and Computational Linguistics, pages 168–186. Springer. find
  29. Pennington, J., Socher, R., and Manning, C. (2014). Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pages 1532– 1543. find
  30. Peters, M. E., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., and Zettlemoyer, L. S. (2018). Deep contextualized word representations. In Proceedings of the 2018 Annual Conference of the North American Chapter of the Association for Computational Linguistics. find
  31. Poesio, M., Stuckardt, R., Versley, Y., and Vieira, R. (2016a). Early approaches to anaphora resolution: Theoretically inspired and heuristic-based. In M. Poesio, et al., editors, Anaphora Resolution: Algorithms, Resources and Applications, chapter 3. Springer. ↗
  32. Poesio, M., Stuckardt, R., and Versley, Y. (2016b). Anaphora Resolution: Algorithms, Resources and Applications. Springer, Berlin. find
  33. Poesio, M., Grishina, Y., Kolhatkar, V., Moosavi, N., Roesiger, I., Roussel, A., Simonjetz, F., Uma, A., Uryupina, O., Yu, J., and Zinsmeister, H. (2018). Anaphora resolution with the arrau corpus. In Proc. of the NAACL Worskhop on Computational Models of Reference, Anaphora and Coreference (CRAC), pages 11– 22, New Orleans, June. find our card
  34. Poesio, M., Chamberlain, J., Paun, S., Yu, J., Uma, A., and Kruschwitz, U. (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. ↗ our card
  35. Pradhan, S., Moschitti, A., Xue, N., Uryupina, O., and Zhang, Y. (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
  36. Rahman, A. and Ng, V. (2011). Narrowing the modeling gap: a cluster-ranking approach to coreference resolution. Journal of Artificial Intelligence Research, 40:469– 521. ↗
  37. Soon, W. M., Lim, D. C. Y., and Ng, H. T. (2001). A machine learning approach to coreference resolution of noun phrases. Computational Linguistics, 27(4), December. ↗ our card
  38. Steinberger, J., Poesio, M., Kabadjov, M., and Jezek, K. (2007). Two uses of anaphora resolution in summarization. Information Processing and Management, 43(6):1663–1680. Special issue on Summarization. ↗
  39. Steinberger, J., Kabadjov, M., and Poesio, M. (2016). Coreference applications to summarization. In Anaphora Resolution: Algorithms, Resources and Applications, chapter 15. Springer. ↗
  40. Taulé, M., Martı́, M. A., and Recasens, M. (2008). Ancora: Multilevel annotated corpora for catalan and spanish. In LREC 2008. Telljohann, H., Hinrichs, E. W., Kübler, S., Zinsmeister, H., and Beck, K. ). Stylebook for the tübingen treebank of written german (tüba-d/z). find
  41. Uryupina, O., Kabadjov, M., and Poesio, M. (2016). Detecting non-reference and non-anaphoricity. In Anaphora Resolution: Algorithms, Resources, and Applications, pages 369–392. Springer, Berlin. ↗
  42. Uryupina, O., Artstein, R., Bristot, A., Cavicchio, F., Delogu, F., Rodriguez, K. J., and Poesio, M. (2019). Annotating a broad range of anaphoric phenomena, in a variety of genres: the ARRAU corpus. Journal of Natural Language Engineering. ↗
  43. Versley, Y., Moschitti, A., Poesio, M., and Yang, X. (2008). Coreference systems based on kernels methods. In Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008), pages 961–968, Manchester, UK, August. Coling 2008 Organizing Committee. find our card
  44. Wiseman, S., Rush, A. M., Shieber, S., and Weston, J. (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), volume 1, pages 1416–1426. find our card
  45. Wiseman, S., Rush, A. M., and Shieber, S. M. (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. find our card
  46. Zhang, R., Nogueira dos Santos, C., Yasunaga, M., Xiang, B., and Radev, D. (2018). 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 (Volume 2: Short Papers), pages 102–107. Association for Computational Linguistics. ↗ our card

↑ back to top

This page in Markdown →