Elamur Research⌕
☰
home / papers / 2023 / Investigating Multilingual Coreference Resolution by Universal Annotations

Investigating Multilingual Coreference Resolution by Universal Annotations

Summary

The paper asks whether the harmonized annotations in CorefUD can reveal properties of coreference shared across languages, and whether such properties help a multilingual coreference resolution (MCR) system. The authors first study the gold training data of CorefUD 1.1 (17 datasets, 12 languages) at three levels: mentions, entities and documents. They also compare genres, using UPOS tags and UD relations to describe mentions and their antecedents. They then analyse the hardest cases left unresolved by the best CRAC 2022 shared task system.

Guided by these findings, they derive features from the universal morphosyntactic annotations and add them to the joint-training baseline of Pražák et al. (2021). The best feature set (ours_wf) gains 0.9 CoNLL F1 on average, while a lemma-based variant (ours_lem) underperforms the baseline.

The work matters because it is presented as the first use of universal annotations for MCR. It shows that cross-lingual regularities exist, though phenomena such as definiteness remain hard to treat uniformly across languages.

Key points

  • Shared patterns:
    • Across languages, the closest antecedent of an overt pronoun is mostly in subject or object position.
    • Hungarian, Lithuanian and Turkish have the most pre-modified mentions, at 51–52%.
  • Mention types by dataset:
    • EN_PARCORFULL, DE_PARCORFULL and FR_DEMOCRAT contain the most overt pronouns, about 46% of mentions.
    • In the Czech datasets, zero pronouns outnumber overt ones.
  • Main common error: In all languages, systems struggle most with two-mention entities, particularly in detecting their nominal noun mentions.
  • Experimental setup:
    • Experiments run on CorefUD 1.0, with roughly 10% of the training data held out as a test set.
    • Results are reported as macro-averaged CoNLL F1 (MUC, B3, CEAFe).
    • LT_LCC and RU_RUCOR are the hardest datasets.
  • Error rates and availability:
    • ours_wf leaves fewer gold entities with zero recall than the baseline (39.19% vs 39.77%).
    • ours_wf also misses fewer mentions than the baseline.
    • Code and model are released at github.com/HaixiaChai/multi-coref.

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

5 papers of our library cite it (of the 140673 whose bibliographies we read); 1 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/v1/2023.findings-emnlp.671 · arXiv 2310.17734

@inproceedings{chai2023investigating,
  title = {{Investigating Multilingual Coreference Resolution by Universal Annotations}},
  author = {Chai, Haixia and Strube, Michael},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2023},
  year = {2023},
  doi = {10.18653/v1/2023.findings-emnlp.671},
  eprint = {2310.17734},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2023.findings-emnlp.671}
}

References

57 references, 33 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Abdulrahman Aloraini and Massimo Poesio. 2020. Anaphoric zero pronoun identification: A multilingual approach. In Proceedings of the Third Workshop on Computational Models of Reference, Anaphora and Coreference, pages 22–32, Barcelona, Spain (online). Association for Computational Linguistics. find our card
  2. Abdulrahman Aloraini and Massimo Poesio. 2021. Data augmentation methods for anaphoric zero pronouns. In Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference, pages 82–93, Punta Cana, Dominican Republic. Association for Computational Linguistics. find
  3. Amit Bagga and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In The First International Conference on Language Resources and Evaluation, pages 563–566, Granada, Spain. find our card
  4. 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. Ass… find our card
  5. Chen Chen and Vincent Ng. 2014. Chinese overt pronoun resolution: A bilingual approach. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 28, pages 1615–1621. find
  6. Shisong Chen, Binbin Gu, Jianfeng Qu, Zhixu Li, An Liu, Lei Zhao, and Zhigang Chen. 2021. Tackling zero pronoun resolution and non-zero coreference resolution jointly. In Proceedings of the 25th Conference on Computational Natural Language Learning, pages 518–527, Online. Association for Computation… find our card
  7. Noam Chomsky. 1993. Lectures on Government and Binding. De Gruyter Mouton, Berlin, New York. find
  8. Marie-Catherine de Marneffe, Christopher D. Manning, Joakim Nivre, and Daniel Zeman. 2021. Universal Dependencies. Computational Linguistics, 47(2):255–308. find our card
  9. 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
  10. Heidrun Dorgeloh and Anja Wanner. 2022. Discourse Syntax. Cambridge University Press. find
  11. Eraldo Fernandes, Cícero dos Santos, and Ruy Milidiú. 2012. Latent structure perceptron with feature induction for unrestricted coreference resolution. In Joint Conference on EMNLP and CoNLL - Shared Task, pages 41–48, Jeju Island, Korea. Association for Computational Linguistics. find our card
  12. Matt Grenander, Shay B. Cohen, and Mark Steedman. 2022. Sentence-incremental neural coreference resolution. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 427–443, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. find
  13. Barbara J. Grosz, Aravind K. Joshi, and Scott Weinstein. 1995. Centering: A framework for modeling the local coherence of discourse. Computational Linguistics, 21(2):203–225. find our card
  14. Jan Hajič, Eduard Bejček, Jaroslava Hlavacova, Marie Mikulová, Milan Straka, Jan Štěpánek, and Barbora Štěpánková. 2020. Prague dependency treebank -consolidated 1.0. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 5208–5218, Marseille, France. European Language… find
  15. Ryu Iida and Massimo Poesio. 2011. A cross-lingual ILP solution to zero anaphora resolution. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 804–813, Portland, Oregon, USA. Association for Computational Linguistics. find our card
  16. Fan Jiang and Trevor Cohn. 2021. Incorporating syntax and semantics in coreference resolution with heterogeneous graph attention network. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1584–1591… find our card
  17. Mandar Joshi, Danqi Chen, Yinhan Liu, Daniel S. Weld, Luke Zettlemoyer, and Omer Levy. 2020. Span-BERT: Improving pre-training by representing and predicting spans. Transactions of the Association for Computational Linguistics, 8:64–77. find our card
  18. 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… find our card
  19. Yuval Kirstain, Ori Ram, and Omer Levy. 2021. Coreference resolution without span representations. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 14–… find our card
  20. Hamidreza Kobdani and Hinrich Schütze. 2010. SU-CRE: A modular system for coreference resolution. In Proceedings of the 5th International Workshop on Semantic Evaluation, pages 92–95, Uppsala, Sweden. Association for Computational Linguistics. find
  21. Fang Kong and Hwee Tou Ng. 2013. Exploiting zero pronouns to improve Chinese coreference resolution. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 278–288, Seattle, Washington, USA. Association for Computational Linguistics. find our card
  22. Frédéric Landragin. 2021. Le corpus Democrat et son exploitation. présentation. Langages, (224):11–24. find
  23. 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), Miyazaki, Japan. European Language Resources Associ… find our card
  24. Ekaterina Lapshinova-Koltunski, Sharid Loáiciga, Christian Hardmeier, and Pauline Krielke. 2019. Cross-lingual incongruences in the annotation of coreference. In Proceedings of the Second Workshop on Computational Models of Reference, Anaphora and Coreference, pages 26–34, Minneapolis, USA. Associat… find
  25. 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
  26. 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. Association for Computational Linguistics. find our card
  27. 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–… find our card
  28. Xiaoqiang Luo. 2005. On coreference resolution performance metrics. In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pages 25–32. find our card
  29. André F. T. Martins. 2015. Transferring coreference resolvers with posterior regularization. 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 1427–1437,… find our card
  30. Anna Nedoluzhko, Michal Novák, Silvie Cinková, Marie Mikulová, and Jiří Mírovský. 2016. Coreference in Prague Czech-English Dependency Treebank. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 169–176, Portorož, Slovenia. European Language… find our card
  31. Anna Nedoluzhko, Michal Novák, Martin Popel, Zdeněk Žabokrtský, Amir Zeldes, Daniel Zeman, Peter Bourgonje, Silvie Cinková, Jan Hajič, Christian Hardmeier, Pauline Krielke, Frédéric Landragin, Ekaterina Lapshinova-Koltunski, M. Antònia Martí, Marie Mikulová, Maciej Ogrodniczuk, Marta Recasens, Man… find
  32. Michal Novák, Anna Nedoluzhko, and Zdeněk Žabokrtský. 2017. Projection-based coreference resolution using deep syntax. In Proceedings of the 2nd Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2017), pages 56–64, Valencia, Spain. Association for Computational Linguistics. find our card
  33. Maciej Ogrodniczuk and Bartłomiej Nitoń. 2017. Improving Polish mention detection with valency dictionary. In Proceedings of the 2nd Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2017), pages 17–23, Valencia, Spain. Association for Computational Linguistics. find
  34. 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 EMNLP and CoNLL - Shared Task, pages 1–40, Jeju Island, Korea. Association for Computational Linguisti… find our card
  35. Ondřej Pražák and Miloslav Konopik. 2022. End-to-end multilingual coreference resolution with mention head prediction. In Proceedings of the CRAC 2022 Shared Task on Multilingual Coreference Resolution, pages 23–27, Gyeongju, Republic of Korea. Association for Computational Linguistics. find our card
  36. Ondřej Pražák, Miloslav Konopík, and Jakub Sido. 2021. Multilingual coreference resolution with harmonized annotations. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 1119–1123. find our card
  37. Altaf Rahman and Vincent Ng. 2012. Translation-based projection for multilingual coreference resolution. In Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 720–730, Montréal, Canada. Association for… find our card
  38. Gorka Urbizu, Ander Soraluze, and Olatz Arregi. 2019. Deep cross-lingual coreference resolution for less-resourced languages: The case of Basque. In Proceedings of the Second Workshop on Computational Models of Reference, Anaphora and Coreference, pages 35–41, Minneapolis, USA. Association for Compu… find our card
  39. Marta Recasens, Lluís Màrquez, Emili Sapena, M. Antònia Martí, Mariona Taulé, Véronique Hoste, Massimo Poesio, and Yannick Versley. 2010. SemEval-2010 task 1: Coreference resolution in multiple languages. In Proceedings of the 5th International Workshop on Semantic Evaluation, pages 1–8, Uppsala, Sw… find our card
  40. Noémi Vadász. 2022. Building a manually annotated Hungarian coreference corpus: Workflow and tools. In Proceedings of the Fifth Workshop on Computational Models of Reference, Anaphora and Coreference, pages 38–47, Gyeongju, Republic of Korea. Association for Computational Linguistics. find our card
  41. Marta Recasens and M Antònia Martí. 2010. Ancora-co: Coreferentially annotated corpora for Spanish and Catalan. Language Resources and Evaluation, 44:315–345. find
  42. Noémi Vadász. 2020. KorKorpusz: kézzel annotált, többrétegű pilotkorpusz építése. In XVI. find
  43. Magyar Számítógépes Nyelvészeti Konferencia (MSZNY 2020), pages 141–154, Szeged. Szegedi Tudománye-gyetem, TTIK, Informatikai Intézet. find
  44. Ina Roesiger and Jonas Kuhn. 2016. IMS HotCoref DE: A data-driven co-reference resolver for German. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 155–160, Portorož, Slovenia. European Language Resources Association (ELRA). find our card
  45. Linfeng Song, Kun Xu, Yue Zhang, Jianshu Chen, and Dong Yu. 2020. ZPR2: Joint zero pronoun recovery and resolution using multi-task learning and BERT. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5429– 5434, Online. Association for Computational L… find our card
  46. Milan Straka and Jana Straková. 2022. ÚFAL CorPipe at CRAC 2022: Effectivity of multilingual models for coreference resolution. In Proceedings of the CRAC 2022 Shared Task on Multilingual Coreference Resolution, pages 28–37, Gyeongju, Republic of Korea. Association for Computational Linguistics. find our card
  47. Vijay Sundar Ram and Sobha Lalitha Devi. 2020. Handling noun-noun coreference in Tamil. In Proceedings of the WILDRE5– 5th Workshop on Indian Language Data: Resources and Evaluation, pages 20–24, Marseille, France. European Language Resources Association (ELRA). find
  48. Fiona Anting Tan, Sujatha Das Gollapalli, and See-Kiong Ng. 2021. NUS-IDS at CASE 2021 task 1: Improving multilingual event sentence coreference identification with linguistic information. In Proceedings of the 4th Workshop on Challenges and Applications of Automated Extraction of Socio-political Ev… find
  49. Svetlana Toldova, A. Roytberg, Alina Ladygina, Maria Vasilyeva, Ilya Azerkovich, Matvei Kurzukov, G. Sim, D.V. Gorshkov, A. Ivanova, Anna Nedoluzhko, and Y. Grishina. 2014. Ru-eval-2014: Evaluating anaphora and coreference resolution for Russian. Komp’juternaja Lingvistika i Intellek-tual’nye Tehnol… find
  50. Marc Vilain, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Sixth Message Understanding Conference (MUC-6): Proceedings of a Conference Held in Columbia, Maryland, November 6-8, 1995. find our card
  51. Juntao Yu, Sopan Khosla, Ramesh Manuvinakurike, Lori Levin, Vincent Ng, Massimo Poesio, Michael Strube, and Carolyn Rosé. 2022. find
  52. The CODI-CRAC 2022 shared task on anaphora, bridging, and discourse deixis in dialogue. In Proceedings of the CODI-CRAC 2022 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue, pages 1–14, Gyeongju, Republic of Korea. Association for Computational Linguistics. find our card
  53. Zdeněk Žabokrtský and Maciej Ogrodniczuk, editors. 2022. Proceedings of the CRAC 2022 Shared Task on Multilingual Coreference Resolution. Association for Computational Linguistics, Gyeongju, Republic of Korea. find
  54. Amir Zeldes. 2017. The GUM Corpus: Creating Multilayer Resources in the Classroom. Language Resources and Evaluation, 51(3):581–612. find
  55. Shulin Zhang, Jixing Li, and John Hale. 2022. Quantifying discourse support for omitted pronouns. In Proceedings of the Fifth Workshop on Computational Models of Reference, Anaphora and Coreference, pages 1–12, Gyeongju, Republic of Korea. Association for Computational Linguistics. find
  56. Huiwei Zhou, Yao Li, Degen Huang, Yan Zhang, Chun-long Wu, and Yuansheng Yang. 2011. Combining syntactic and semantic features by SVM for unrestricted coreference resolution. In Proceedings of the Fifteenth Conference on Computational Natural Language Learning: Shared Task, pages 66–70, Portland, Or… find
  57. Voldemaras Žitkus and Rita Butkiene. 2018. Coreference annotation scheme and corpus for lithuanian language. In 2018 Fifth International Conference on Social Networks Analysis, Management and Security (SNAMS), pages 243–250. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/chai-2023-investigating-multilingual-coreference-resolution-universal/