Elamur Research⌕
☰
home / papers / 2018 / A Deterministic Algorithm for Bridging Anaphora Resolution

A Deterministic Algorithm for Bridging Anaphora Resolution

Summary

Bridging anaphora resolution links an anaphor to an antecedent through association rather than identity. For example, "distribution arrangements" can be tied to earlier-mentioned "dialysis products." Earlier systems estimated relatedness from preposition-pattern co-occurrence counts over head nouns only, so they missed what modifiers contribute. Hou's embeddings PP captured noun association but covered only nouns.

This paper concatenates embeddings PP with standard 100-dimensional GloVe vectors. Words missing from either source are padded with a constant filler vector. The result is a broader 200-dimensional resource called embeddings bridging. On top of it, the author builds a training-free, deterministic resolver. It represents each NP by averaging the vectors of its head and selected modifiers, then picks the best-scoring candidate antecedent.

On ISNotes, this simple method comes close to the feature-heavy Markov Logic Network system of Hou et al. (2013b). Combining the two yields a new best accuracy. Modest results on BASHI and ARRAU, achieved with only small adaptations, suggest the resource generalizes. That matters because it lets bridging resolution be applied to new English corpora without supervised training.

Key points

  • The resource: embeddings bridging has 200 dimensions and 532,768 entries covering all word types, versus 276,326 nouns in embeddings PP. It is publicly released on Zenodo.
  • How embeddings PP was built: it was trained on about 197 million noun pairs drawn from prepositional and possessive NP structures in parsed Gigaword. A "_PP" suffix on head nouns encodes the asymmetry between head and modifier.
  • ISNotes accuracy:
    • Deterministic approach alone: 39.52%
    • MLN model II: 41.32%
    • MLN II + embeddings PP (Hou, 2018): 45.85%
    • MLN II + embeddings bridging: 46.46% (best)
  • Other corpora:
    • BASHI: 27.43%, or 29.94% when comparative anaphors are excluded
    • ARRAU (RST) test set: 32.39%, compared with 39.8% for a modified rule-based system by Rösiger (2018b)
  • Stated limitation: knowledge contained within the NP is sometimes insufficient. Future work aims to use context beyond the NP.

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

14 papers of our library cite it (of the 140673 whose bibliographies we read); 6 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/d18-1219 · arXiv 1811.05721

@inproceedings{hou2018deterministic,
  title = {{A Deterministic Algorithm for Bridging Anaphora Resolution}},
  author = {Hou, Yufang},
  booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing},
  year = {2018},
  doi = {10.18653/v1/d18-1219},
  eprint = {1811.05721},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/d18-1219}
}

References

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

  1. I.I. Bejar, R. Chaffin, and S.E. Embretson. 1991. Cognitive and psychometric analysis of analogical problem solving. Springer-Verlag. find
  2. Danqi Chen, Jason Bolton, and Christopher D. Manning. 2016. A thorough examination of the CNN/Daily mail reading comprehension task. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Berlin, Germany, 7–12 August 2016, pages 2358–2367. find our card
  3. Pedro Domingos and Daniel Lowd. 2009. Markov Logic: An Interface Layer for Artificial Intelligence. Morgan Claypool Publishers. find
  4. Yufang Hou. 2016. Incremental fine-grained information status classification using attention-based LSTMs. In Proceedings of the 26th International Conference on Computational Linguistics, Osaka, Japan, 11–16 December 2016, pages 1880–1890. find
  5. Yufang Hou. 2018. Enhanced word representations for bridging anaphora resolution. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, New Orleans, Louisiana, 1–6 June 2018, pages 1–7. find our card
  6. Yufang Hou, Katja Markert, and Michael Strube. 2013a. Cascading collective classification for bridging anaphora recognition using a rich linguistic feature set. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, Wash., 18–21 October 2013, pages 814– 8… find our card
  7. Yufang Hou, Katja Markert, and Michael Strube. 2013b. Global inference for bridging anaphora resolution. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Atlanta, Georgia, 9–14 June 2013, pages 907–917. find our card
  8. 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, Copenhagen, Denmark, 7–11 November 2017, pages 188–197. find our card
  9. Katja Markert, Yufang Hou, and Michael Strube. 2012. Collective classification for fine-grained information status. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, Jeju Island, Korea, 8–14 July 2012, pages 795–804. find our card
  10. Katja Markert, Malvina Nissim, and Natalia N. Mod-jeska. 2003. Using the web for nominal anaphora resolution. In Proceedings of the EACL Workshop on the Computational Treatment of Anaphora. Budapest, Hungary, 14 April 2003, pages 39–46. find
  11. Tomas Mikolov, Ilya Sutskever, Kai Chen, Gregory S. Corrado, and Jeffrey Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems 26 (NIPS 2013), pages 3111–3119. find
  12. Courtney Napoles, Matthew Gormley, and Benjamin Van Durme. 2012. Annotated Gigaword. In Proceedings of the Joint Workshop on Automatic Knowledge Base Construction & Web-scale Knowledge Extraction (AKBC-WEKEX) Montréal, Québec, Canada, 7-8 June 2012, pages 95–100. find
  13. Robert Parker, David Graff, Junbo Kong, Ke Chen, and Kazuaki Maeda. 2011. English Gigaword Fifth Edition. LDC2011T07. find
  14. Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, 25–29 October 2014, pages 1532–1543. find
  15. Yufang Hou, Katja Markert, and Michael Strube. 2014. A rule-based system for unrestricted bridging resolution: Recognizing bridging anaphora and finding links to antecedents. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, 25–29 October 2014, p… find our card
  16. Massimo Poesio, Yulia Grishina, Varada Kolhatkar, Nafise Sadat Moosavi, Ina Rösiger, Adam Roussel, Fabian Simonjetz, Alexandra Uma, Olga Uryupina, Juntao Yu, and Heike Zinsmeister. 2018. Anaphora resolution with the ARRAU corpus. In Proceedings of the Workshop on Computational Models of Reference,… find our card
  17. David A. Jurgens, Peter D. Turney, Saif M. Mohammad, and Keith J. Holyoak. 2012. Semeval-2012 task 2: Measuring degrees of relational similarity. In Proceedings of the First Joint Conference on Lexical and Computational Semantics, Montréal, Canada, 7–8 June 1999, pages 356–364. find
  18. Massimo Poesio, Rahul Mehta, Axel Maroudas, and Janet Hitzeman. 2004. Learning to resolve bridging references. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics, Barcelona, Spain, 21–26 July 2004, pages 143–150. find our card
  19. Emmanuel Lassalle and Pascal Denis. 2011. Leveraging different meronym discovery methods for bridging resolution in French. In Proceedings of the 8th Discourse Anaphora and Anaphor Resolution Colloquium (DAARC 2011), Faro, Algarve, Portugal, 6– 7 October 2011, pages 35–46. find
  20. Massimo Poesio and Renata Vieira. 1998. A corpus-based investigation of definite description use. Computational Linguistics, 24(2):183–216. find
  21. Massimo Poesio, Renata Vieira, and Simone Teufel. 1997. Resolving bridging references in unrestricted text. In Proceedings of the ACL Workshop on Operational Factors in Practical, Robust Anaphora Resolution for Unrestricted Text, Madrid, Spain, July 1997, pages 1–6. find our card
  22. Tim Rocktäschel, Edward Grefenstette, Karl Moritz Hermann, Tomas Kocisky, and Phil Blunsom. 2016. Reasoning about entailment with neural attention. In Proceedings of the 4th International Conference on Learning Representations, San Juan, Puerto Rico, 2-4 May 2016. find our card
  23. Ina Rösiger. 2018a. BASHI: A corpus of wall street journal articles annotated with bridging links. In Proceedings of the 11th International Conference on Language Resources and Evaluation, Miyazaki, Japan, 7–12 May 2018, pages 382–388. find our card
  24. Ina Rösiger. 2018b. Rule- and learning-based methods for bridging resolution in the ARRAU corpus. In Proceedings of the Workshop on Computational Models of Reference, Anaphora and Coreference. New Orleans, Louisiana, June 6, 2018, pages 23–33. find our card
  25. Ina Rösiger, Arndt Riester, and Jonas Kuhn. 2018. Bridging resolution: Task definition, corpus resources and rule-based experiments. In Proceedings of the 27th International Conference on Computational Linguistics, Santa Fe, New-Mexico, USA, 20–26 August 2018, pages 3516–3528. find our card
  26. Sabine Schulte im Walde. 1998. Resolving bridging descriptions in high-dimensional space. Master’s thesis, University of Edinburgh, Centre for Cognitive Science. find
  27. Ralph Weischedel, Martha Palmer, Mitchell Marcus, Eduard Hovy, Sameer Pradhan, Lance Ramshaw, Nianwen Xue, Ann Taylor, Jeff Kaufman, Michelle Franchini, Mohammed El-Bachouti, Robert Belvin, and Ann Houston. 2011. OntoNotes release 4.0. LDC2011T03, Philadelphia, Penn.: Linguistic Data Consortium. find
  28. Ian H. Witten and Eibe Frank. 2005. Data Mining: Practical Machine Learning Tools and Techniques, 2nd edition. Morgan Kaufmann, San Francisco, Cal. find
  29. Alisa Zhila, Scott Wen-tau Yih, Geoffrey Zweig, Chris Meek, and Tomas Mikolov. 2013. Combining heterogeneous models for measuring relational similarity. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,… find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/hou-2018-deterministic-algorithm-bridging-anaphora-resolution/