Elamur Research⌕
☰
home / papers / 2017 / Projection-based Coreference Resolution Using Deep Syntax

Projection-based Coreference Resolution Using Deep Syntax

Summary

The paper addresses coreference resolution for German and Russian when no coreference-annotated data exist in those languages. The system was created as a submission to the CORBON 2017 Shared task, competing in its closed-track setting. Their approach uses English-German and English-Russian parallel corpora in three stages. First, the English side is annotated automatically by the Berkeley Entity Resolution system, plus a Treex heuristic for relative pronouns. Next, mentions and their entity IDs are carried over to the target side using GIZA++ word alignment computed on lemmatized text. Finally, these projected links serve as training data for a target-language resolver. Unlike earlier projection work, the resolver runs on the tectogrammatical (deep-syntax) layer of the Treex framework. It uses separate models for each mention type, which requires converting mentions from surface spans to tree nodes and back again. The team was the only participant. They scored 29.40 (German) and 30.94 (Russian) CoNLL points on the official test set. A stage-by-stage analysis found that projection is the main source of quality loss. The work shows how far annotation transfer can go for languages that lack coreference resources.

Key points

  • Official results: CoNLL score of 29.40 for German and 30.94 for Russian on the official evaluation set. On the additional dev set (DevAdd), the scores were 22.4 and 31.8.
  • Projection coverage: About 90% of English mentions are projected. A mention is transferred only if its aligned target tokens form a contiguous span.
  • German preprocessing: MATE tools handle lemmatization, tagging and parsing. HamleDT converts the output to Prague style. NameTag, trained on NoSta-D, provides named entities.
  • Russian preprocessing: UDPipe, trained on SynTagRus in Prague style, does the parsing, with lemmas from TreeTagger. NameTag, trained on an extended Persons-1000, provides named entities.
  • Quality relative to English: The Russian resolver keeps 66% of the English resolver's CoNLL quality (48.1 points), while the German one keeps only 46%. Ablation experiments show that the models for PP3 pronouns and NPs contribute the most.

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

4 papers of our library cite it (of the 140673 whose bibliographies we read); 1 of them have a page here, 3 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/w17-1508

@inproceedings{novak2017projection,
  title = {{Projection-based Coreference Resolution Using Deep Syntax}},
  author = {Novák, Michal and Nedoluzhko, Anna and Žabokrtský, Zdeněk},
  booktitle = {Proceedings of the 2nd Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2017)},
  year = {2017},
  doi = {10.18653/v1/w17-1508},
  url = {https://doi.org/10.18653/v1/w17-1508}
}

References

32 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Greg Durrett and Dan Klein. 2014. A Joint Model for Entity Analysis: Coreference, Typing, and Linking. TACL, 2:477–490. find our card
  2. Mariana S. C. Almeida, Cláudia Pinto, Helena Figueira, Pedro Mendes, and André F. T. Martins. 2015. Aligning Opinions: Cross-Lingual Opinion Mining with Dependencies. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conferen… find
  3. CORBON 2017 Shared Task: Projection-Based Coreference Resolution. In The 15th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference, Vol. 1 (Long Papers), Stroudsburg, PA, USA. Association for Computational Linguistics. find
  4. 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
  5. Amit Bagga and Breck Baldwin. 1998. Algorithms for Scoring Coreference Chains. In In The First International Conference on Language Resources and Evaluation Workshop on Linguistics Coreference, pages 563–566. find our card
  6. Xiaoqiang Luo. 2005. On Coreference Resolution Performance Metrics. In Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, pages 25–32, Stroudsburg, PA, USA. Association for Computational Linguistics. find our card
  7. Darina Benikova, Chris Biemann, and Marc Reznicek. 2014. NoSta-D Named Entity Annotation for German: Guidelines and Dataset. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), Reykjavik, Iceland. European Language Resources Association (ELRA). find
  8. 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 of the Asian Federation of Natural Langua… find our card
  9. Anders Björkelund, Bernd Bohnet, Love Hafdell, and Pierre Nugues. 2010. A High-performance Syntactic and Semantic Dependency Parser. In Proceedings of the 23rd International Conference on Computational Linguistics: Demonstrations, pages 33– 36, Stroudsburg, PA, USA. Association for Computational Li… find
  10. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. In Proceedings of Workshop at ICLR. find
  11. Igor Boguslavsky, Svetlana Grigorieva, Nikolai Grig-oriev, Leonid Kreidlin, and Nadezhda Frid. 2000. Dependency Treebank for Russian: Concept, Tools, Types of Information. In Proceedings of the 18th Conference on Computational Linguistics-Volume 2, pages 987–991, Morristown, NJ, USA. Association for… find
  12. Valerie Mozharova and Natalia Loukachevitch. 2016. Two-stage Approach in Russian Named Entity Recognition. In Proceedings of the International FRUCT Conference on Intelligence, Social Media and Web (ISMW FRUCT 2016), pages 43–48, Saint Petersburg. find
  13. Bernd Bohnet and Joakim Nivre. 2012. A Transition-based System for Joint Part-of-speech Tagging and Labeled Non-projective Dependency Parsing. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 1455–1465,… find
  14. Franz J. Och and Hermann Ney. 2000. Improved Statistical Alignment Models. In Proceedings of the 38th Annual Meeting on Association for Computational Linguistics, pages 440–447, Stroudsburg, PA, USA. Association for Computational Linguistics. find our card
  15. Maciej Ogrodniczuk. 2013. Translation- and Projection-Based Unsupervised Coreference Resolution for Polish. In Language Processing and Intelligent Information Systems, number 7912, pages 125–130, Berlin / Heidelberg. Springer. find
  16. José G. C. de Souza and Constantin Orăsan. 2011. Can Projected Chains in Parallel Corpora Help Coreference Resolution? In Proceedings of the 8th International Conference on Anaphora Processing uation, pages 3132–3139, Istanbul, Turkey. European Language Resources Association (ELRA). find
  17. Sebastian Padó and Mirella Lapata. 2009. Cross-lingual Annotation Projection of Semantic Roles. Journal of Artificial Intelligence Research, 36(1):307–340. find
  18. Petr Sgall, Eva Hajičová, Jarmila Panevová, and Jacob Mey. 1986. The meaning of the sentence in its semantic and pragmatic aspects. Springer. find
  19. Martin Popel and Zdeněk Žabokrtský. 2010. TectoMT: Modular NLP Framework. In Proceedings of the 7th International Conference on Advances in Natural Language Processing, pages 293–304, Berlin, Heidelberg. Springer-Verlag. find
  20. Milan Straka, Jan Hajič, and Jana Straková. 2016. UDPipe: Trainable Pipeline for Processing CoNLL-U Files Performing Tokenization, Morphological Analysis, POS Tagging and Parsing. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 4290– 4297,… find our card
  21. Oana Postolache, Dan Cristea, and Constantin Orăsan. 2006. Transferring Coreference Chains through Word Alignment. In Proceedings of the Fifth International Conference on Language Resources and Evaluation, pages 889–892, Genoa, Italy. European Language Resources Association. find our card
  22. Jana Straková, Milan Straka, and Jan Hajič. 2014. Open-Source Tools for Morphology, Lemmatization, POS Tagging and Named Entity Recognition. In Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 13–18, Baltimore, Maryland. Association… find
  23. 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 Empirical Methods in Natural Language Processing and Computational Natural Language Learning - Proceed… find our card
  24. Oscar Täckström, Dipanjan Das, Slav Petrov, Ryan T. McDonald, and Joakim Nivre. 2013. Token and Type Constraints for Cross-Lingual Part-of-Speech Tagging. TACL, 1:1–12. find
  25. Jörg Tiedemann. 2012. Parallel Data, Tools and Interfaces in OPUS. In Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC’12), pages 2214–2218, Paris, France. European Language Resources Association. find
  26. Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Hwee Tou Ng, Anders Bjrkelund, Olga Uryupina, Yuchen Zhang, and Zhi Zhong. 2013. Towards Robust Linguistic Analysis using OntoNotes. In Proceedings of the Seventeenth Conference on Computational Natural Language Learning, pages 143– 152, Sofia, Bulg… find
  27. Marc Vilain, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A Model-theoretic Coreference Scoring Scheme. In Proceedings of the 6th Conference on Message Understanding, pages 45–52, Stroudsburg, PA, USA. Association for Computational Linguistics. find our card
  28. Sameer Pradhan, Xiaoqiang Luo, Marta Recasens, Eduard Hovy, Vincent Ng, and Michael Strube. 2014. Scoring Coreference Partitions of Predicted Mentions: A Reference Implementation. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pag… find our card
  29. Daniel Zeman, Ondřej Dušek, David Mareček, Martin Popel, Loganathan Ramasamy, Jan Štěpánek, Zdeněk Žabokrtský, and Jan Hajič. 2014. HamleDT: Harmonized Multi-Language Dependency Treebank. Language Resources and Evaluation, 48(4):601–637. find
  30. 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 968–977, Stroudsburg, PA, USA. Association… find our card
  31. Helmut Schmid. 1995. Improvements In Part-of-Speech Tagging With an Application To German. In In Proceedings of the ACL SIGDAT-Workshop, pages 47–50, Stroudsburg, PA, USA. Association for Computational Linguistics. find
  32. Wolfgang Seeker and Jonas Kuhn. 2012. Making Ellipses Explicit in Dependency Conversion for a German Treebank. In Proceedings of the Eight International Conference on Language Resources and Eval- find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/novak-2017-projection-based-coreference-resolution-deep/