Elamur Research⌕
☰
home / papers / 2009 / A Probabilistic Model for Associative Anaphora Resolution

A Probabilistic Model for Associative Anaphora Resolution

Summary

The paper tackles associative anaphora in Japanese. This is a bridging relation where an anaphoric noun (e.g., "the roof", "the price") depends on an earlier, non-coreferent entity (a house, a car model) for its meaning. String matching and salience help little here, so the authors focus on broad lexical knowledge. They build nominal case frames (NCFs) automatically from "N_m no N_h" phrases in a very large Japanese Web Corpus. Each frame lists the obligatory entities a noun needs to be interpreted. Resolution then treats the missing entity as a zero pronoun attached to the noun. This lets the same probabilistic model handle zero anaphora and associative anaphora together. Example slots are generalized with JUMAN semantic categories and named-entity classes. Joint resolution clearly outperforms resolving associative anaphora alone, and generalized examples add a substantial gain. This matters because it shows that Web-scale lexical resources plus a unified zero-anaphora framework can handle bridging phenomena in a pro-drop language.

Key points

  • The NCFs were built using the Web Corpus compiled by Kawahara and Kurohashi (2006). The corpus has 1.6 billion unique sentences, about 390 million "N_m no N_h" phrases and around 564,000 nouns with frames.
  • A manual check of 100 frequent nouns gave NCF precision 0.89, recall 0.74 and F-measure 0.81.
  • The best setup combined generalized examples with automatic zero anaphora resolution. It reached recall 0.518 (57/110), precision 0.363 and F-measure 0.427.
  • Joint resolution with zero anaphora added 0.072 F-measure over no resolution (0.355). Gold zero anaphora relations raised it to 0.458.
  • Dropping the generalized examples cost about 0.14 F-measure. Category generalization contributed most, while named-entity generalization helped only slightly.

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

7 papers of our library cite it (of the 140673 whose bibliographies we read); 3 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.

@inproceedings{sasano2009probabilistic,
  title = {{A Probabilistic Model for Associative Anaphora Resolution}},
  author = {Sasano, Ryohei and Kurohashi, Sadao},
  booktitle = {Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing},
  year = {2009},
  doi = {10.3115/1699648.1699692},
  url = {https://doi.org/10.3115/1699648.1699692}
}

References

26 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Razvan Bunescu. 2003. Associative anaphora resolution: A web-based approach. In Proc. of EACL’03: Workshop on The Computational Treatment of Anaphora, pages 47–52. find
  2. Herbert H Clark. 1975. Bridging. In Proc. of the Conference on Theoretical Issues in Natural Language Processing, pages 169–174. find
  3. Caroline Gasperin and Ted Briscoe. 2008. Statistical anaphora resolution in biomedical texts. In Proc. of COLING’08, pages 257–264. find our card
  4. Caroline Gasperin and Renata Vieira. 2004. Using word similarity lists for resolving indirect anaphora. In Proc. of ACL’04: Workshop on Reference Resolution and its Applications, pages 40–46. find our card
  5. Udo Hahn, Michael Strube, and Katja Markert. 1996. Bridging textual ellipsis. In Proc. of COLING’96, pages 496–501. find
  6. John A. Hawkins. 1978. Definiteness and indefiniteness: a study in reference and grammaticality prediction. Croom Helm Ltd. find
  7. IREX Committee, editor. 1999. Proc. of the IREX Workshop. find
  8. Daisuke Kawahara and Sadao Kurohashi. 2002. Fertilization of case frame dictionary for robust Japanese case analysis. In Proc. of COLING’02, pages 425– 431. find
  9. Daisuke Kawahara and Sadao Kurohashi. 2006. Case frame compilation from the web using high-performance computing. In Proc. of LREC’06, pages 1344–1347. find
  10. Sadao Kurohashi and Yasuyuki Sakai. 1999. Semantic analysis of Japanese noun phrases: A new approach to dictionary-based understanding. In Proc. of ACL’99, pages 481–488. find
  11. Shalom Lappin and Herbert J. Leass. 1994. An algorithm for pronominal anaphora resolution. Computational Linguistics, 20(4):535–562. find our card
  12. Katja Markert, Malvina Nissim, and Natalia N Modjeska. 2003. Using the web for nominal anaphora resolution. In Proc. of EACL’03: Workshop on the Computational Treatment of Anaphora, pages 39– 46. find
  13. Josef Meyer and Robert Dale. 2002. Using the Word-Net hierarchy for associative anaphora resolution. In Proc. of SemaNet’02: Building and Using Semantic Networks. find
  14. Ruslan Mitkov, Richard Evans, and Constantin Orăsan. 2002. A new, fully automatic version of Mitkov’s knowledge-poor pronoun resolution method. In Proc. of CICLing’02. find
  15. Natalia N Modjeska. 2002. Lexical and grammatical role constraints in resolution other-anaphora. In Proc. of DAARC’02. find
  16. Masaki Murata, Hitoshi Isahara, and Makoto Nagao. 1999. Resolution of indirect anaphora in Japanese sentences using examples “X no Y”(Y of X). In Proc. of ACL’99: Workshop on Coreference and Its Applications. find
  17. Massimo Poesio, Tomonori Ishikawa, Sabine Schulte im Walde, and Renata Vieira. 2002. Acquiring lexical knowledge for anaphora resolution. In Proc. of LREC’02, pages 1220–1224. find our card
  18. Massimo Poesio, Pahul Mehta, Axel Maroudas, and Janet Hitzeman. 2004. Learning to Resolve Bridging References. In Proc. of ACL’04, pages 143–150. find our card
  19. Ryohei Sasano and Sadao Kurohashi. 2008. Japanese named entity recognition using structural natural language processing. In Proc. of IJCNLP’08, pages 607–612. find
  20. Ryohei Sasano, Daisuke Kawahara, and Sadao Kurohashi. 2004. Automatic construction of nominal case frames and its application to indirect anaphora resolution. In Proc. of COLING’04, pages 1201– 1207. find
  21. Ryohei Sasano, Daisuke Kawahara, and Sadao Kurohashi. 2008. A fully-lexicalized probabilistic model for japanese zero anaphora resolution. In Proc. of COLING’08, pages 769–776. find our card
  22. Ryohei Sasano, Daisuke Kawahara, and Sadao Kurohashi. 2009. The effect of corpus size on case frame acquisition for discourse analysis. In Proc. of NAACL-HLT’09, pages 521–529. find
  23. Michael Strube and Udo Hahn. 1999. Functional centering – grounding referential coherence in information structure. Computational Linguistics, 25(3):309–344. find our card
  24. Renata Vieira and Massimo Poesio. 2000. An empirically based system for processing definite descriptions. Computational Linguistics, 26(4):539–592. find
  25. Renata Vieira, Eckhard Bick, Jorge Coelho, Vinicius Muller, Sandra Collovini, Jose Souza, and Lucia Rino. 2006. Semantic tagging for resolution of indirect anaphora. In Proc. of the 7th SIGdial Workshop on Discourse and Dialogue, pages 76–79. find
  26. Mitsuko Yamura-Takei. 2003. Approaches to zero adnominal recognition. In Proc. of ACL’03: Student Research Workshop, pages 87–94. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/sasano-2009-probabilistic-model-associative-anaphora-resolution/