Coreference resolution of Korean anaphoric zero objects: Towards a supervised machine learning approach

AUTHORS

Euhee Kim,Shinhan University and Dongguk University
Myung-Kwan Park,

ABSTRACT

We propose a supervised machine learning model for automatic coreference resolution of anaphoric zero objects (AZOs) in so-called radical pro-drop languages. Concentrating on Korean, we aim to take as input the AZOs in the discourse-theoretically annotated corpus and resolve each of them. To fully specify our model, the context features employed in Park, Lim and Hong (2015) were adopted. We initially trained our supervised resolver on a set of training data by using supervised learning algorithms. After training, we then applied the resulting model to resolve AZOs. The experiments demonstrate that our supervised model outdoes its rivaling supervised counterparts in performance when resolving AZOs in the given corpus.

 

KEYWORDS

anaphoric zero object, coreference resolution, Centering Theory, context features, supervised machine learning.

REFERENCES

[1]      B. J. Grosz, S. Weinstein, and A. K. Joshi, Centering: A framework for modeling the local coherence of discourse. Computational linguistics, Vol. 21, No. 2, pp. 203-225 (1995)
[2]      M. Hong, Centering theory and argument deletion in spoken Korean, The Korean Journal Cognitive Science Vol. 11, No. 1, pp. 9-24, (in Korean) (2000)
[3]      M. K Kim, Zero vs. overt NPs in Korean discourse: A centering analysis. Korean Journal of Linguistics Vol. 28, No.1, pp. 29-49, (2003)
[4]      A. Fischer and C. Igel, An introduction to restricted Boltzmann machines, in Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, pp. 14-36, Springer, (2012)
[5]      M. Iida, Discourse coherence and shifting centers in Japanese texts, in Centering Theory in Discourse, Edited M. A. Walker, A. K. Joshi, and E. F. Prince, pp. 161-180, Oxford, (1998)
[6]      M. Kameyama, Intra-sentential centering: A case study, in Centering Theory in Discourse, Edited M. A. Walker, A. K. Joshi, and E. F. Prince, eds., pp. 89-112, Oxford, (1998)
[7]      B. J. Grosz, A. K. Joshi, and S. Weinstein, Providing a unified account of definite noun phrases in discourse, in Proceedings, 21st Annual Meeting of the Association of Computational Linguistics, pp. 44-50, (1983)
[8]      F. Keller and M. Lapata, Object drop and discourse accessibility, in Proceedings of the 17th West Coast Conference on Formal Linguistics, pp. 362-374. (1998).
[9]      A. Park, S. Lim, and M. Hong, Zero object resolution in Korean, in Proceedings of the 29th Pacific Asia Conference on Language Information and Computing, pp. 439-448 (2015)
[10]   M. Walker, S. Cote, and M. Iida, Japanese discourse and the process of centering, in Proceedings of Computational linguistics Vol. 20, No. 2, pp. 193-232 (1994)

CITATION

  • APA:
    Kim,E.& Park,M.K.(2016). Coreference resolution of Korean anaphoric zero objects: Towards a supervised machine learning approach. International Journal of Computer Science and Information Technology for Education, 1(1), 1-6. 10.21742/IJCSITE.2016.1.1.01
  • Harvard:
    Kim,E., Park,M.K.(2016). "Coreference resolution of Korean anaphoric zero objects: Towards a supervised machine learning approach". International Journal of Computer Science and Information Technology for Education, 1(1), pp.1-6. doi:10.21742/IJCSITE.2016.1.1.01
  • IEEE:
    [1] E.Kim, M.K.Park, "Coreference resolution of Korean anaphoric zero objects: Towards a supervised machine learning approach". International Journal of Computer Science and Information Technology for Education, vol.1, no.1, pp.1-6, Dec. 2016
  • MLA:
    Kim Euhee and Park Myung-Kwan. "Coreference resolution of Korean anaphoric zero objects: Towards a supervised machine learning approach". International Journal of Computer Science and Information Technology for Education, vol.1, no.1, Dec. 2016, pp.1-6, doi:10.21742/IJCSITE.2016.1.1.01

ISSUE INFO

  • Volume 1, No. 1, 2016
  • ISSN(p):2205-8370
  • ISSN(e):2207-5372
  • Published:Dec. 2016

DOWNLOAD