ETRI Journal

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Korean Coreference Resolution with Guided Mention Pair Model Using Deep Learning

  • Park, Cheoneum (Department of Computer Science, Kangwon National University) ;
  • Choi, Kyoung-Ho (Department of Computer Science, Kangwon National University) ;
  • Lee, Changki (Department of Computer Science, Kangwon National University) ;
  • Lim, Soojong (SW & Content Research Laboratory, ETRI)
  • Received : 2015.10.08
  • Accepted : 2016.06.21
  • Published : 2016.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

The general method of machine learning has encountered disadvantages in terms of the significant amount of time and effort required for feature extraction and engineering in natural language processing. However, in recent years, these disadvantages have been solved using deep learning. In this paper, we propose a mention pair (MP) model using deep learning, and a system that combines both rule-based and deep learning-based systems using a guided MP as a coreference resolution, which is an information extraction technique. Our experiment results confirm that the proposed deep-learning based coreference resolution system achieves a better level of performance than rule- and statistics-based systems applied separately

Keywords

References

  1. H. Lee et al., "Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules," Comput. Linguistics, vol. 39, no. 4, 2013, pp. 885-916. https://doi.org/10.1162/COLI_a_00152
  2. C.-E. Park, K.-H Choi, and C. Lee, "Korean Coreference Resolution using the Multi-pass Sieve," J. KIISE, vol. 41, no. 11, Nov. 2014, pp. 992-1005. https://doi.org/10.5626/JOK.2014.41.11.992
  3. A. Haghighi and D. Klein, "Coreference Resolution in a Modular, Entity-centered Model," Human Language Technol.: Annu. Conf. North American Chapter Assoc. Comput. Linguistics, Los Angeles, CA, USA, June 1-6, 2010, pp. 385-393.
  4. A. Rahman and V. Ng, "Supervised Models for Coreference Resolution," Proc. Conf. Empirical Methods Natural Language Process., Singapore, Aug. 6-7, 2009, pp. 968-977.
  5. K.-H. Choi, C.-E. Park, and C. Lee, "Coreference Resolution for Korean using Mention Pair with SVM," KIIES Trans. Comput. Practices, vol. 21, no. 4, Apr. 2015, pp. 333-337. https://doi.org/10.5626/KTCP.2015.21.4.333
  6. S. Pradhan et al., "Conll-2011 Shared Task: Modeling Unrestricted Coreference in Ontonotes," Proc. Conf. Comput. Natural Language Learning: Shared Task, Portland, OR, USA, June 23-24, 2011, pp. 1-27.
  7. C. Lee et al., "Korean Dependency Parsing using Deep Learning," Annu. Conf. Human Cognitive Language Technol., Chuncheon, Rep. of Korea, Oct. 7, 2014, pp. 87-91.
  8. R. Collobert et al. "Natural Language Processing (almost) from Scratch," J. Mach. Learn. Res., vol. 12, 2011, pp. 2493-2537.
  9. G.E. Hinton, S. Osindero, and Y.-W. Teh, "A Fast Learning Algorithm for Deep Belief Nets," Neural Comput., vol. 18, no. 7, May 2006, pp. 1527-1554. https://doi.org/10.1162/neco.2006.18.7.1527
  10. G.E. Hinton et al., Improving Neural Networks by Preventing Co-adaptation of Feature Detectors, CoRR, Accessed 2014. https://arxiv.org/abs/1207.0580
  11. X. Glorot, A. Bordes, and Y. Bengio, "Deep Sparse Rectifier Neural Networks," Proc. Int. Conf. Artif. Intell. Statistics, vol. 15, 2011, pp. 315-323.
  12. C. Noam, Lectures on Government and Binding, Berlin, Germany: Mouton de Gruyter, 1981.
  13. Y.-C. Yoon, et al., "Construction of Korean Acronym Dictionary by Considering Ways of Making Acronym From Definition," Proc. KSCS, 2006, pp. 81-85.
  14. B.J. Grosz, S. Weinstein, and A.K. Joshi, "Centering: A Framework for Modeling the Local Coherence of Discourse," Comput. Linguistics, vol. 21, no. 2, 1995, pp. 203-225.
  15. S. Lappin and H.J. Leass, "An Algorithm for Pronominal Anaphora Resolution," Comput. Linguistics, vol. 20, no. 4, 1994, pp. 535-561.
  16. M. Vilain et al., "A Model-Theoretic Coreference Scoring Scheme," MUC6 Proc. Conf. Message understanding, Columbia, MA, USA, Nov. 1995, pp. 45-52.
  17. A. Bagga and B. Baldwin, "Algorithms for Scoring Coreference Chains," Int. Conf. Language Resources Evaluation Workshop Linguistics Coref., Granada, Spain, May, 1998, pp. 563-566.
  18. X. Luo, "On Coreference Resolution Performance Metrics," Proc. Conf. Human Language Technol. Empirical Methods Natural Language Process., Vancouver, Canada, Oct. 2005, pp. 25-32.
  19. E.R. Fernandes, C.N. Dos Santos, and R.L. Milidiu, "Latent Structure Perceptron with Feature Induction for Unrestricted Coreference Resolution," Joint Conf. EMNLP CoNLL-Shared Task, Jeju, Rep. of Korea, July 12-4, 2012, pp. 41-48.
  20. C. Chen and V. Ng, "Combining the Best of Two Worlds: A Hybrid Approach to Multilingual Coreference Resolution," Joint Conf. EMNLP CoNLL-Shared Task, Jeju, Rep. of Korea, July 2-4, 2012, pp. 56-63.
  21. H. Lee et al., "Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules," Comput. Linguistics, vol. 39, no. 4, Nov. 2013, pp. 885-916. https://doi.org/10.1162/COLI_a_00152
  22. K. Clark and C.D. Manning, "Entity-Centric Coreference Resolution with Model Stacking," Proc. Annu. Meeting Assoc. Comput. Linguistics Int. Joint Conf. Natural Language Process., Beijing, China, July 27-31, 2015, pp. 1405-1415.
  23. Z. Chen, H. Ji, and R. Haralick, "Event Coreference Resolution: Algorithm, Feature Impact and Evaluation," Proc. Events Emerging Text Types, Stroudsburg, PA, USA, 2009, pp. 1-8.
  24. F. Rahimian, S. Girdzijauskas, and S. Haridi, "Parallel Community Detection for Cross-Document Coreference," Web Intell. Intell. Agent Technol, Warsaw, Poland, Aug. 11-14, 2014, pp. 46-53.

Cited by

  1. Mention Detection Using Pointer Networks for Coreference Resolution vol.39, pp.5, 2017, https://doi.org/10.4218/etrij.17.0117.0140
  2. Restricting Answer Candidates Based on Taxonomic Relatedness of Integrated Lexical Knowledge Base in Question Answering vol.39, pp.2, 2016, https://doi.org/10.4218/etrij.17.2816.0066
  3. 포인터 네트워크를 이용한 한국어 의존 구문 분석 vol.44, pp.8, 2016, https://doi.org/10.5626/jok.2017.44.8.822
  4. 계층적 포인터 네트워크를 이용한 상호참조해결 vol.23, pp.9, 2016, https://doi.org/10.5626/ktcp.2017.23.9.542
  5. 포지션 인코딩 기반 스택 포인터 네트워크를 이용한 한국어 상호참조해결 vol.24, pp.3, 2016, https://doi.org/10.5626/ktcp.2018.24.3.113
  6. Layer-wise hint-based training for knowledge transfer in a teacher-student framework vol.41, pp.2, 2016, https://doi.org/10.4218/etrij.2018-0152
  7. Simple and effective neural coreference resolution for Korean language vol.43, pp.6, 2021, https://doi.org/10.4218/etrij.2020-0282