Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Top > JACIII > Semantic Representation for Understanding Meaning Based on Cor ...

single-jc.php

JACIII Vol.10 No.6 pp. 876-912
doi: 10.20965/jaciii.2006.p0876
(2006)

Paper:

Views over last 60 days: 600

Semantic Representation for Understanding Meaning Based on Correspondence Between Meanings

Akira Takagi*,**, Hideki Asoh**, Yukihiro Itoh***,
Makoto Kondo***, and Ichiro Kobayashi****

*CSK Systems Corp., 2-26-1 Minami-Aoyama, Minato-ku, Tokyo 107-0062, Japan

**National Institute of Advanced Industrial Science and Technology, 1-1-1 Umezono, Tsukuba, Ibaraki 305-8568, Japan

***Faculty of Informatics, Shizuoka University, 3-5-1 Jouhoku, Hamamatu-shi, Shizuoka 432-8011, Japan

****Faculty of Science, Ochanomizu University, 2-1-1 Otsuka, Bunkyo-ku, Tokyo 112-8610, Japan

Received:
February 23, 2006
Accepted:
May 17, 2006
Published:
November 20, 2006
Creative Commons License
Keywords:
semantic representation, interpretation of dependency relation, interpretation within a clause/sentence, interpretation beyond a clause/sentence, natural language understanding
Abstract
One of the biggest problems in natural language processing is that its processing target (i.e. the surface expressions of sentences) has a great deal of diversity. In order to reduce the difficulty, it is desirable to extract the semantic content denoted by a sentence in such a way that it does not depend on the surface expressions as much as possible. This paper proposes a new semantic representation and general interpretive procedures that enable us to obtain the result of semantic interpretation from a variety of surface expressions of the input independently of their dependency structures. In the semantic representation to be proposed, a variety of surface dependency relations are compressed into attribute nouns, and the meaning expressed by dependency relation is represented in a uniform style (i.e. attribute = value). This approach enables us to establish correspondence between meanings by using the attribute-value pair as a basic unit. With this semantic representation and the general interpretive procedures, the same interpretive result can be obtained from sentences with different dependency structures. We will further demonstrate that semantic contents of multiple sentences can be integrated by interpreting them based on the correspondence between meanings.
Cite this article as:
A. Takagi, H. Asoh, Y. Itoh, M. Kondo, and I. Kobayashi, “Semantic Representation for Understanding Meaning Based on Correspondence Between Meanings,” J. Adv. Comput. Intell. Intell. Inform., Vol.10 No.6, pp. 876-912, 2006.
Data files:
References
  1. [1] J. Allen, “Natural Language Understanding,” The Benjamin/Cummings Publishing Company, Inc., 1987.
  2. [2] J. Bresnan (Ed.), “The Mental Representation of Grammatical Relations,” MIT Press, Cambridge, Massachusetts, 1982.
  3. [3] A. Copestake, D. Flickinger, I. A. Sag, and C. Pollard, “Minimal Recursion Semantics,” An Introduction, draft, CSLI Stanford Univ., 1999.
  4. [4] D. R. Dowty, R. E. Wall, and S. Peters, “Introduction to Montague Semantics,” D. Reidel Publishing Corp., 1981.
  5. [5] K. Furukawa (Ed.), “Shizen Gengo no Kiso Riron (Fundamental Theory of Natural Language),” Kyoritsu Shuppan, Tokyo, 1986 (in Japanese).
  6. [6] G. Gazdar, E. Klein, G. K. Pullnm, and I. A. Sag, “Generalized Phrase Structure Grammar,” Blackwell Publishing, Oxford, England, and Harvard University Press, Cambridge, Massachusetts, 1985.
  7. [7] D. Jurafsky and J. H. Martin, “Speech and Language Processing – An Introduction to Natural Language Processing,” Computational Linguistics, and Speech Recognition, Prentice Hall, 2000.
  8. [8] C. S. Mellish, “Computer Interpretation of Natural Language Descriptions,” Ellis Horwood Ltd., Publisher, Chichester, England, 1985.
  9. [9] M. Minsky, “A Framework for Representing Knowledge. in The Psychology of Computer Vision,” P. H. Winston (ed.), McGraw-Hill, 1975.
  10. [10] M. Nagao, “Shizengengo Shori (Natural Language Processing),” Iwanami Shoten, 1996 (in Japanese).
  11. [11] D. A. Norman and D. E. Rumlhart, “Explorations in Cognition,” Freeman, W. H. Co. 1975.
  12. [12] P. Norvig, “Marker Passing as a Weak Method for Text Inferencing,” Cognitive Science, Vol.13, pp. 569-620, 1989.
  13. [13] C. Pollard and I. A. Sag, “Information-Based Syntax and Semantics,” Volume 1 Fundamentals, CSLI, Stanford Univ., Stanford, California, 1987.
  14. [14] M. R. Quillian, “Semantic Memory,” in Semantic Information Processing, M. Minsky (Ed.), MIT Press, Cambridge, Massachusetts, 1968.
  15. [15] I. A. Sag and T. Wasow, “Syntactic Theory: a Formal Introduction,” CSLI Publications, Stanford, California, 1999.
  16. [16] R. C. Schank, “Conceptual Information Processing,” North-Holland, 1975.
  17. [17] A. Takagi and Y. Itoh, “Shizen Gengo no Shori (Processing Natural Language),” Maruzen, 1987 (in Japanese).
  18. [18] A. Takagi, H. Asoh, H. Nakashima, Y. Itoh, and I. Kobayashi, “A semantic representation of dialogue systems considering dependency relations and semantic structural mapping,” IPSJ SIG Technical Reports, 2004-SLP-54(46), 2004 (in Japanese).
  19. [19] H. Tanaka (Ed.), “Natural Language Processing and Its Applications,” IEICE Press, Tokyo, 1999 (in Japanese).
  20. [20] M. F. McTear, “Spoken dialogue technology: enabling the conversational user interface,” ACM Computing Surveys, Vol.34, No.1, pp. 90-169, 2002.
  21. [21] T. Winograd, “Understanding Natural Language,” Academic Press, New York, 1972.

Creative Commons License  This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Nov. 04, 2024