Elamur Research⌕
☰
home / papers / 2015 / Intra-sentential Zero Anaphora Resolution using Subject Sharing Recognition

Intra-sentential Zero Anaphora Resolution using Subject Sharing Recognition

Summary

In pro-drop languages such as Japanese, subjects are frequently omitted, which makes zero anaphora resolution important for machine translation and information extraction. This paper addresses intra-sentential cases, where an omitted subject has its antecedent in the same sentence. The authors observe that many such cases involve predicates sharing one subject. They train a pairwise recognizer that uses local context to decide whether two predicates in a sentence have the same subject. Three restricted pair types are covered: DEP, ADJ and PNP. Recognized pairs are linked into a subject shared predicate network (SSPN). An SVM-based subject detector then finds a realized subject in the network, and that subject is propagated, possibly over several links, to predicates whose subject is empty. Cases left unresolved are passed to the ILP-based method of Iida and Poesio (2011). On a modified NAIST Text Corpus, the combined system significantly outperforms the ILP baseline alone. The authors describe this as the first explicit use of an independent subject sharing recognizer for zero anaphora resolution.

Key points

  • Within the NAIST Text Corpus, subject sharing accounts for about 39% of zero anaphors whose antecedents lie in the same sentence, and roughly 84% of such within-sentence zero anaphors in the corpus are subjects.
  • The subject detector uses SVM light with a 2nd-degree polynomial kernel. It was trained on 35,304 positive and 104,250 negative instances and reached an F-score of 0.899 (recall 0.949, precision 0.855).
  • Using SSPN propagation alone on 8,473 subject-to-subject zero anaphors, the best F-score was 0.456, obtained with DEP + ADJ + PNP. Transitive propagation through the SSPN generally beat single-link propagation.
  • The full pipeline was evaluated on 18,324 subject zero anaphors. The best variant, DEP + PNP, scored 0.380 F versus 0.344 for the baseline, and the gain was significant under McNemar's test (p < 0.01).
  • Without the ILP fallback, SSPN-only variants keep precision of about 60–75%. This makes them attractive for precision-oriented uses such as information extraction.

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

15 papers of our library cite it (of the 140673 whose bibliographies we read); 7 of them have a page here, 8 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/d15-1260

@inproceedings{iida2015intra,
  title = {{Intra-sentential Zero Anaphora Resolution using Subject Sharing Recognition}},
  author = {Iida, Ryu and Torisawa, Kentaro and Hashimoto, Chikara and Oh, Jong-Hoon and Kloetzer, Julien},
  booktitle = {Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing},
  year = {2015},
  doi = {10.18653/v1/d15-1260},
  url = {https://doi.org/10.18653/v1/d15-1260}
}

References

31 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Mohit Bansal and Dan Klein. 2012. Coreference semantics from web features. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, pages 389–398. find our card
  2. David Bean and Ellen Riloff. 2004. Unsupervised learning of contextual role knowledge for coreference resolution. In Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, pages 297–304. find our card
  3. Chen Chen and Vincent Ng. 2013. Chinese zero pronoun resolution: Some recent advances. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1360–1365. find our card
  4. Barbara J. Grosz, Scott Weinstein, and Aravind K. Joshi. 1995. Centering: A framework for modeling the local coherence of discourse. Computational Linguistics, 21(2):203–225. find our card
  5. Masatsugu Hangyo, Daisuke Kawahara, and Sadao Kurohashi. 2013. Japanese zero reference resolution considering exophora and author/reader mentions. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 924–934. find
  6. Zellig Harris. 1954. Distributional structure. Word, 10(23):146–162. find
  7. Chikara Hashimoto, Kentaro Torisawa, Julien Kloetzer, Motoki Sano, István Varga, Jong-Hoon Oh, and Yutaka Kidawara. 2014. Toward future scenario generation: Extracting event causality exploiting semantic relation, context, and association features. In Proceedings of the 52nd Annual Meeting of the A… find
  8. Yuta Hayashibe, Mamoru Komachi, and Yuji Matsumoto. 2011. Japanese predicate argument structure analysis exploiting argument position and type. In Proceedings of 5th International Joint Conference on Natural Language Processing, pages 201–209. find
  9. Thomas Hofmann. 1999. Probabilistic latent semantic indexing. In Processing of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 50–57. find
  10. 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. find our card
  11. Ryu Iida, Kentaro Inui, and Yuji Matsumoto. 2007a. Zero-anaphora resolution by learning rich syntactic pattern features. ACM Transactions on Asian Language Information Processing, Volume 6. Issue 4, Article 12. find
  12. Ryu Iida, Mamoru Komachi, Kentaro Inui, and Yuji Matsumoto. 2007b. Annotating a Japanese text corpus with predicate-argument and coreference relations. In Proceedings of the ACL Workshop: ‘Linguistic Annotation Workshop’, pages 132–139. find our card
  13. Kenji Imamura, Kuniko Saito, and Tomoko Izumi. 2009. Discriminative approach to predicate-argument structure analysis with zero-anaphora resolution. In Proceedings of the ACL-IJCNLP 2009 Conference Short Papers, pages 85–88. find our card
  14. Hideki Isozaki and Tsutomu Hirao. 2003. Japanese zero pronoun resolution based on ranking rules and machine learning. In Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing, pages 184–191. find our card
  15. Megumi Kameyama. 1986. A property-sharing constraint in centering. In Proceedings of the 24th Annual Meeting of the Association for Computational Linguistics, pages 200–206. find
  16. Jun’ichi Kazama and Kentaro Torisawa. 2008. Inducing gazetteers for named entity recognition by large-scale clustering of dependency relations. In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 407–415. find
  17. Hiromi Nakaiwa and Satoshi Shirai. 1996. Anaphora resolution of Japanese zero pronouns with deictic reference. In Proceedings of the 16th International Conference on Computational Linguistics, pages 812–817. find our card
  18. Manabu Okumura and Kouji Tamura. 1996. Zero pronoun resolution in Japanese discourse based on Centering Theory. In Proceedings of the 16th International Conference on Computational Linguistics, pages 871–876. find our card
  19. Motoki Sano, Kentaro Torisawa, Julien Kloetzer, Chikara Hashimoto, István Varga, and Jong-Hoon Oh. 2014. Million-scale derivation of semantic relations from a manually constructed predicate taxonomy. In Proceedings of the 25th International Conference on Computational Linguistics, pages 1423– 1434. find
  20. Ryohei Sasano, Daisuke Kawahara, and Sadao Kurohashi. 2008. A fully-lexicalized probabilistic model for Japanese zero anaphora resolution. In Proceedings of the 22nd International Conference on Computational Linguistics, pages 769–776. find our card
  21. Ryohei Sasano, Daisuke Kawahara, and Sadao Kurohashi. 2009. The effect of corpus size on case frame acquisition for discourse analysis. In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 521–… find
  22. Kazuhiro Seki, Atsushi Fujii, and Tetsuya Ishikawa. 2002. A probabilistic method for analyzing Japanese anaphora integrating zero pronoun detection and resolution. In Proceedings of the 19th International Conference on Computational Linguistics, pages 911–917. find our card
  23. Hirotoshi Taira, Sanae Fujita, and Masaaki Nagata. 2008. A Japanese predicate argument structure analysis using decision lists. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 523–532. find
  24. Vladimir N. Vapnik. 1998. Statistical Learning Theory. Adaptive and Learning Systems for Signal Processing, Communications, and Control. John Wiley & Sons. find
  25. Marilyn Walker, Sharon Cote, and Masayo Iida. 1994. Japanese discourse and the process of centering. Computational Linguistics, 20(2):193–233. find
  26. Yotaro Watanabe, Masayuki Asahara, and Yuji Matsumoto. 2010. A structured model for joint learning of argument roles and predicate senses. In Proceedings of the ACL 2010 Conference Short Papers, pages 98–102. find
  27. Xiaofeng Yang, Jian Su, and Chew Lim Tan. 2005. Improving pronoun resolution using statistics-based semantic compatibility information. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics, pages 165–172. find our card
  28. Katsumasa Yoshikawa, Masayuki Asahara, and Yuji Matsumoto. 2011. Jointly extracting Japanese predicate-argument relation with Markov logic. In Proceedings of 5th International Joint Conference on Natural Language Processing, pages 1125–1133. find
  29. Naoki Yoshinaga and Masaru Kitsuregawa. 2009. Polynomial to linear: Efficient classification with conjunctive features. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 1542–1551. find
  30. Koichiro Yoshino, Shinsuke Mori, and Tatsuya Kawahara. 2013. Predicate argument structure analysis using partially annotated corpora. In Proceedings of the 6th International Joint Conference on Natural Language Processing, pages 957–961. find
  31. Shanheng Zhao and Hwee Tou Ng. 2007. Identification and resolution of Chinese zero pronouns: A machine learning approach. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 541–550. find our card

↑ back to top