Journal of KIISE:Software and Applications (한국정보과학회논문지:소프트웨어및응용)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지

Generation of Zero Pronouns using Center Transition of Preceding Utterances

선행 발화의 중심 전이를 이용한 영형 생성

  • 노지은 (포항공과대학교 컴퓨터공학과) ;
  • 나승훈 (포항공과대학교 컴퓨터공학과) ;
  • 이종혁 (포항공과대학교 컴퓨터공학과)
  • Published : 2005.10.01
Download PDF
⟨ Previous Next ⟩

Abstract

To generate coherent texts, it is important to produce appropriate pronouns to refer to previously-mentioned things in a discourse. Specifically, we focus on pronominalization by zero pronouns which frequently occur in Korean. This paper investigates zero pronouns in Korean based on the cost-based centering theory, especially focusing on the center transitions of adjacent utterances. In previous centering works, only one type of nominal entity has been considered as the target of pronominalization, even though other entities are frequently pronominalized as zero pronouns. To resolve this problem, and explain the reference phenomena of real texts, four types of nominal entity (Npair, Ninter, Nintra, and Nnon) from centering theory are defined with the concept of inter-, intra-, and pairwise salience. For each entity type, a case study of zero phenomena is performed through analyzing corpus and building a pronominalization model. This study shows that the zero phenomena of entities which have been neglected in previous centering works are explained via the renter transition of the second previous utterance. We also show that in Ninter, Nintra, and Nnon, pronominalization accuracy achieved by complex combination of several types of features is completely or nearly achieved by using the second previous utterance's transition across genres.

자연스러운 텍스트를 생성하기 위해서는, 한번 언급된 대상을 지시하기 위한 대용화(pronominalization)과정이 필수적이며, 특히 한국어에 빈번히 발생하는 영형(zero pronoun)을 자연스럽게 생성하는 것이 중요하다. 본 논문에서는, 비용기반 중심화 이론(cost-based centering theory)을 적용하여, 선행 발화의 중심 전이(center transition)가 현 발화의 영형에 미치는 영향을 살펴본다. 이를 위해, 영형으로 실현될 수 있는 명사를 중심화 이론에 기반해 문장간 현저성, 문장내 현저성, 문장간/내 현저성을 가지는지의 여부로 4가지 유형(Npair, Ninter, Nintra, Nnon)으로 정의하고, 유형별로 영형 현상을 고찰하였다. 그 결과, 기존에 중심화 이론에서 배제되었던 명사들이 선행 발화의 중심 전이로 설명될 수 있음을 밝혔다. 또, 선행 발화의 중심 전이를 이용한 영형 생성 모델을 구축하여 다양한 자질을 적용한 영형 생성 모델의 성능과 비교하였다.

Keywords

References

  1. M. Ariel, 'Accessing noun phrase antecedents,' Routledge, London (Croom Helm Linguistics series), 1990
  2. W. Chafe, Discourse, consciousness, and time, University of Chicago Press, Chicago, IL: London, 1994
  3. E.F. Prince, Towards a taxonomy of given-new information, pp.223-225, in P.Cole(ed,), Radical Pragmatics, Academic Press, New York, N.Y., 1981
  4. J.K. Gundel, N. Hedberg, and R. Zacharski, 'Cognitive status and the form of referring expressions in discourse,' Proc. Language, Vol.69, no.2, pp.279-307, 1993 https://doi.org/10.2307/416535
  5. M.A.K. Haliday, 'Notes on transitivity and theme in English,' Proc. Linguistics, vol.3, no.2, pp.199-244, 1967 https://doi.org/10.1017/S0022226700016613
  6. B.J. Grosz, A.K. Joshi, and S. Weinstein, 'Centering: a framework for modeling the local coherence of discourse,' Proc. Computational Linguistics vol.21, no.2, pp.203-225, 1995
  7. H. Cheng, 'Experimenting with the interaction between aggregation and text planning,' Proc. ANLP-NAACL Student Research Workshop, USA. 2000
  8. V. Mittal, J. Moore, G. Carenini, and S. Roth, 'Describing complex charts in natural language: a caption generation system,' Proc. Computational Linguistics, Special issue on Natural Language Generation, vol.24, no.3, pp.431-467, 1998
  9. R. Kibble and R. Power, 'Using centering theory to plan coherent texts,' Proc. 12th Amsterdam colloquium, pp.187-192, 1999
  10. R. Kibble and R. Power, 'An integrated frame-work for text planning and pronominalization,' Proc. 1st International Natural Language Generation, Mitzpe Ramon, Israel, pp.77-84, 2000
  11. Y. T. Mitsuko, M. Fujiwara, and T. Aizawa, 'Centering as an anaphora generation algorithm: a language learning aid perspective,' Proc. 6th Natural Language Processing Pacific Rim, Tokyo, Japan, pp.557-562, 2001
  12. R. Prasad, 'Constraints on the generation of referring expressions, with special reference to Hindi,' U of Pennsylvania, PhD Thesis, 2003
  13. J.E. Roh and J.H. Lee, 'An empirical study for generating zero pronoun in Korean based on Cost-based Centering Model,' Proc. Australasian Language Technology Association, Melbourne, Australia, pp.90-97, 2003
  14. J,E. Roh and J,H. Lee, 'Generation of natural referring expressions by syntactic information and Cost-based Centering Model,' Journal of KISS: Software and Applications, vol.21, no.12, pp.1649-1659, 2004
  15. M.Y. Kim, 'The centering of Korean discourse,' Seoul National University, M.S. Thesis, 1994
  16. M.K. Kim, 'Conditions on deletion in Korean based on information packaging,' Proc. Discourse and Cognition, vol.1, no.2, pp.61-88, 1999
  17. B.R. Ryu, 'Centering and zero anaphora in the Korean discourse,' Seoul National University, M.S. Thesis, 2001
  18. 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
  19. R. Henschel, H. Cheng, and M. Poieso, 'Pronominalization revisited,' Proc. 18th International Conf. on Computational Linguistics, Saarbruecken, pp.306-312, 2000 https://doi.org/10.3115/990820.990865
  20. M. Strube and U. Hahn, 'Functional centering: grounding referential coherence in information structure,' Proc. Computational Linguistics, vol.25, no.3, pp.309-344, 1999
  21. M. Walker, M. Iida, and S. Cote, 'Japanese discourse and the process of centering,' Proc. Computational Linguistics, vol.20, no.2, pp.193-232, 1994
  22. R.J. Passonneau, 'Getting and keeping the center of attention,' In Bates, M. and Weischedel, R.R., editors, Challenges in Natural Language Processing, Cambridge University Press, pp.179-227, 1993
  23. D. Byron and A. Stent, 'A preliminary model of centering in dialog,' Proc. 36th Annual Meeting of the Association for Computational Linguistics, Montreal, Canada, pp.1475-1477, August. 1998 https://doi.org/10.3115/980691.980811
  24. B. Di Eugenio, 'Centering in Italian,' In Walker, M.A., Joshi, A.K., and Prince, E.F., editors, Centering Theory in Discourse, chapter 7, pp.115-138, Oxford, 1998
  25. M. Kameyama, 'Intra-sentential centering: a case study,' In Walker, M.A., Joshi, A.K., and Prince, E.F., editors, Centering Theory in Discourse, chapter 6, pp.89-112, Oxford, 1998
  26. J.R. Tetreault, 'A corpus-based evaluation of centering and pronoun resolution,' Proc. Computational Linguistics, vol.2, no.4, pp.507-520, 2001 https://doi.org/10.1162/089120101753342644
  27. M. Poesio, R. Stevenson, H. Cheng, B.D. Eugenio, and J. Hitzeman, 'Centering: a parametric theory and its instantiations,' Proc. Computational Linguistics, vol.30, no.3, pp.309-363, 2004 https://doi.org/10.1162/0891201041850911
  28. K.F. McCoy and M. Strube, 'Generating anaphoric expressions: pronoun or definite description?,' Proc. Workshop on the Relation of Discourse/Dialogue Structure and Reference, held in conjunction with Annual Meeting of the Association for Computational Linguistics, pp.63-71, 1999
  29. M. Strube, and M. Wolters, 'A probabilistic genre-independent model of pronominalization,' Proc. 1st Meeting of the North American Chapter of the Association for Computational Linguistics, Seattle, WA, USA, pp.18-25, April. 2000
  30. R. Stevenson, 'The role of salience in the production of referring expressions,' In Kees van Deemter and Rodger Kibble(eds), Information Sharing, CSLI Publications, 2002
  31. B.K. Lee, 'The effect of verb causality upon pronoun disambiguation in sentences with causal, adversative, and conjunctive relation,' Department of Psychology Graduate School of Seoul National University, M.S Thesis, 1989
  32. H.E. Yun, 'The sentence reading time and the comprehension of anaphoric pronouns as a function of the causality implicit in verbs,' Department of Psychology Graduate School of Seoul National University, M.S Thesis, 1984
  33. H.R. Kwon, 'The effects of semantic factors upon comprehension of relative-clause sentence: the semantic factors of co-reference and cause,' Department of psychology graduate school of Seoul National University, M.S. Thesis, 1988