Elamur Research⌕
☰
home / papers / 2012 / Translation-Based Projection for Multilingual Coreference Resolution

Translation-Based Projection for Multilingual Coreference Resolution

Summary

Supervised coreference resolution requires costly hand-annotated corpora for every new language, and rule-based or unsupervised alternatives require linguistic expertise in that language. Rahman and Ng test whether coreference-annotated data for a target language can be produced automatically, with no target-language coreference labels and no knowledge of the language. Their pipeline has three steps: machine-translate target-language text into English, run an existing English resolver on the translation, and map the resulting mentions and chains back through word alignments. They study three settings that differ in how much target-language tooling is available, from none at all to a mention extractor plus training a resolver on the projected (noisy) chains. In experiments on Spanish and Italian, the strongest configuration reaches roughly 90% of the average F-score of fully supervised resolvers. The authors present projection as a way to ease the annotation bottleneck by supplementing manual annotation, not by replacing it. It applies to languages that have MT, parallel text and a mention extractor but lack coreference corpora.

Key points

  • Pipeline: GoogleTranslate for translation, Reconcile (pre-trained on the Wolverhampton corpus) as a black-box English resolver, and GIZA++ alignments trained on Europarl plus the translated texts. The alignment data were Porter-stemmed and supplemented with a bilingual dictionary built from OmegaWiki, Wiktionary and Universal Dictionary, together with identical-word entries.
  • Mention projection: a projected mention is the smallest span covering all aligned target words, following Yarowsky and Ngai (2001). Mentions are processed left to right so that no target span is claimed twice.
  • Training on projected labels: a resolver trained on projected annotations (Setting 3) beats direct projection (Setting 2) in average F-score.
    • With true mentions, the gain is +5.3 for Spanish and +0.7 for Italian.
    • With system mentions, the gain is +4.9 for Spanish and +2.8 for Italian.
    • The improvement comes mainly from higher MUC recall.
  • Comparison with supervised systems: Setting 3 reaches 93–94% of the supervised average F-score for Spanish and 89–91% for Italian. Evaluation uses MUC, B3, CEAF and BLANC.
  • Error pattern: recall loss is larger under MUC than under B3 and CEAF. This suggests the approach handles singleton clusters better than it recovers coreference links.

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

18 papers of our library cite it (of the 140673 whose bibliographies we read); 8 of them have a page here, 10 not yet.

Cite

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

@inproceedings{rahman2012translation,
  title = {{Translation-Based Projection for Multilingual Coreference Resolution}},
  author = {Rahman, Altaf and Ng, Vincent},
  booktitle = {Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  year = {2012},
  url = {https://aclanthology.org/N12-1090/}
}

References

35 references, 20 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Giuseppe Attardi, Maria Simi, and Stefano Dei Rossi. 2010. TANL-1: Coreference resolution by parse analysis and similarity clustering. In Proceedings of the 5th International Workshop on Semantic Evaluation, pages 108–111. find our card
  2. Amit Bagga and Breck Baldwin. 1998. Entity-based cross-document coreferencing using the vector space model. In Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and the 17th International Conference on Computational Linguistics, pages 79–85. find
  3. Jennifer Camargo de Souza and Constantine Orasan. 2011. Can projected chains in parallel corpora help coreference resolution? In Anaphora Processing and Applications, pages 59–69. Springer. find
  4. Dipanjan Das and Slav Petrov. 2011. Unsupervised part-of-speech tagging with bilingual graph-based projections. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 600–609. find
  5. Pascal Denis and Jason Baldridge. 2008. Specialized models and ranking for coreference resolution. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 660–669. find our card
  6. Aria Haghighi and Dan Klein. 2007. Unsupervised coreference resolution in a nonparametric bayesian model. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, pages 848–855. find our card
  7. Aria Haghighi and Dan Klein. 2010. Coreference resolution in a modular, entity-centered model. In Proceedings of Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 385–393. find our card
  8. Sanda Harabagiu and Steven Maiorano. 2000. Multilingual coreference resolution. In Proceedings of the Sixth Applied Natural Language Processing Conference, pages 142–149. find our card
  9. Rebecca Hwa, Philip Resnik, Amy Weinberg, Clara Cabezas, and Okan Kolak. 2005. Bootstrapping parsers via syntactic projection across parallel texts. Natural Language Engineering, 11(3):311–325. find
  10. Thorsten Joachims. 1999. Making large-scale SVM learning practical. In Bernhard Schölkopf, Christopher Burges, and Alexander Smola, editors, Advances in Kernel Methods – Support Vector Learning, pages 44–56. MIT Press, Cambridge, MA. find
  11. 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. find
  12. Hamidreza Kobdani, Hinrich Schütze, Michael Schiehlen, and Hans Kamp. 2011. Bootstrapping coreference resolution using word associations. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 783–792. find our card
  13. Philipp Koehn. 2005. Europarl: A parallel corpus for statistical machine translation. In Proceedings of MT Summit X. find
  14. Xiaoqiang Luo, Abe Ittycheriah, Hongyan Jing, Nanda Kambhatla, and Salim Roukos. 2004. A mention-synchronous coreference resolution algorithm based on the Bell tree. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics, pages 135–142. find our card
  15. 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
  16. Rada Mihalcea, Carmen Banea, and Janyce Wiebe. 2007. Learning multilingual subjective language via cross-lingual projections. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, pages 976–983.. find
  17. Ruslan Mitkov. 1999. Multilingual anaphora resolution. Machine Translation, 14(3–4):281–299. find
  18. Vincent Ng and Claire Cardie. 2002. Improving machine learning approaches to coreference resolution. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 104–111. find our card
  19. Vincent Ng. 2008. Unsupervised models for coreference resolution. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 640–649. find our card
  20. Franz Josef Och and Hermann Ney. 2000. Improved statistical alignment models. In Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics. find
  21. Hoifung Poon and Pedro Domingos. 2008. Joint unsupervised coreference resolution with Markov Logic. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 650– 659. find our card
  22. Martin F. Porter. 1980. An algorithm for suffix stripping. Program, 14(3):130–137. find
  23. Oana Postolache, Dan Cristea, and Constantin Orasan. 2006. Transferring coreference chains through word alignment. In Proceedings of the Fifth International Conference on Language Resources and Evaluation, pages 889–892. find our card
  24. Karthik Raghunathan, Heeyoung Lee, Sudarshan Rangarajan, Nate Chambers, Mihai Surdeanu, Dan Jurafsky, and Christopher Manning. 2010. A multi-pass sieve for coreference resolution. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 492–501. find our card
  25. Altaf Rahman and Vincent Ng. 2009. Supervised models for coreference resolution. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 968–977. find our card
  26. Marta Recasens and Eduard Hovy. 2011. BLANC: Implementing the Rand Index for coreference evaluation. Natural Language Engineering, 17(4):485–510. find
  27. Marta Recasens, Lluı́s Màrquez, Emili Sapena, M. Antònia Martı́, 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. find our card
  28. Philip Resnik. 2004. Exploiting hidden meanings: Using bilingual text for monolingual annotation. In Proceedings of the 5th International Conference on Computational Linguistics and Intelligent Text Processing, pages 283–299. find
  29. 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
  30. 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
  31. Veselin Stoyanov, Claire Cardie, Nathan Gilbert, Ellen Riloff, David Buttler, and David Hysom. 2010. Coreference resolution with reconcile. In Proceedings of the ACL 2010 Conference Short Papers, pages 156–161. find our card
  32. Marc Vilain, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proceedings of the Sixth Message Understanding Conference, pages 45–52. find our card
  33. Xiaofeng Yang, Jian Su, Jun Lang, Chew Lim Tan, and Sheng Li. 2008. An entity-mention model for coreference resolution with inductive logic programming. In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 843–851. find our card
  34. David Yarowsky and Grace Ngai. 2001. Inducing multilingual POS taggers and NP bracketers via robust projection across aligned corpora. In Proceedings of the Second Meeting of the North American Chapter of the Association for Computational Linguistics, pages 200–207. find
  35. Imed Zitouni and Radu Florian. 2008. Mention detection crossing the language barrier. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 600–609. find

↑ back to top

This page in Markdown →