›› 2010, Vol. 25 ›› Issue (5): 1030-1039.doi: 10.1007/s11390-010-1081-8

• Artificial Intelligence • Previous Articles     Next Articles

Unsupervised WSD by Finding the Predominant Sense Using Context as a Dynamic Thesaurus

Javier Tejada-Cárcamo1, Hiram Calvo2,3, Alexander Gelbukh2, and Kazuo Hara3   

  1. 1. San Pablo Catholic University, Arequipa, Peru;
    2. Center for Computing Research, National Polytechnic Institute, Mexico City, 07738, Mexico;
    3. Nara Institute of Science and Technology, Takayama, Ikoma, Nara 630-0192, Japan
  • Received:2009-06-12 Revised:2010-06-23 Online:2010-09-01 Published:2010-09-01
  • About author:
    Javier Tejada-Cárcamo was born in Perú in 1976. He obtained his Master's degree in computer science (with honors) in 2005 from the Center for Computing Research (CIC) of the National Polytechnic Institute (IPN), Mexico,and his Ph.D. degree in computer science (with honors) in 2009 at the same Center.Since 2010 he is an associated professor and researcher at San Pablo Catholic University in Arequipa. Peru. He works as project leader at Research and Software Development Center of the San Agustin National University in Arequipa, Peru.
    Hiram Calvo was born in Mexico in 1978. He obtained his Master's degree in computer science in 2002 from National Autonomous University of Mexico (UNAM), with a thesis on mathematical modeling, and his Ph.D. degree in computer science (with honors) in 2006 from CIC of IPN, Mexico.Since 2006 he is a lecturer at CIC of IPN. He was awarded with the Lázaro Cárdenas Prize in 2006 as the best Ph.D. candidate of IPN in the area of physics and mathematics. This Prize was handed personally by the President of Mexico. Currently he is a visiting researcher at the Nara Institute of Science and Technology, Japan. He is a JSPS fellow.
    Alexander Gelbukh holds a honors M.Sc. degree in mathematics from the Moscow State Lomonosov University, Russia, 1990, and Ph.D. degree in computer science from the All-Russian Institute for Scientific and Technical Information, Russia, 1995. He has been a research fellow at the All-Union Center for Scientific and Technical Information, Moscow, Russia|distinguished visiting professor at Chung-Ang University, Seoul, Korea, and is currently research professor and head of the Natural Language Processing Laboratory of the Center for Computing Research of the National Polytechnic Institute, Mexico, and invited professor of the National University, Bogota, Colombia. He is an academician of the Mexican Academy of Sciences, National Researcher of Mexico, and the executive board secretary of the Mexican Society for Artificial Intelligence. His recent awards include the prestigious Research Diploma from the National Polytechnic Institute, Mexico. His main areas of interest are computational linguistics and artificial intelligence. He is author, co-author or editor of more than 400 publications|member of editorial board or reviewer for a number of international journals. He has been program committee member of about 150 international conferences and Chair, Honorary Chair, or Program Committee Chair of more than 20 international conferences, as well as principal investigator of several projects, funded governmentally or internationally, in the field of computational linguistics and information retrieval.
    Kazuo Hara was born in Tokyo, Japan, in 1971. He received his Master's degree of engineering from the University of Tokyo, and his Ph.D. degree from Nara Institute of Science and Technology. His research interests include natural language processing aiming for information extraction, such as coordinate structure analysis and word sense disambiguation. Previously he was the team leader in Sankyo Co., LTD, the 2nd largest pharmacy company in Japan, where he composed statistical analysis plans and performed statistical hypothetical testing for new drug candidate compositions in clinical trials. He has experience in bioinformatics and statistics as well. Currently he is a postdoctoral researcher at the Nara Institute of Science and Technology, Japan.
  • Supported by:

    Supported by the Mexican Government (SNI, SIP-IPN, COFAA-IPN, and PIFI-IPN), CONACYT and the Japanese Government.

We present and analyze an unsupervised method for Word Sense Disambiguation (WSD). Our work is based on the method presented by McCarthy et al. in 2004 for finding the predominant sense of each word in the entire corpus. Their maximization algorithm allows weighted terms (similar words) from a distributional thesaurus to accumulate a score for each ambiguous word sense, i.e., the sense with the highest score is chosen based on votes from a weighted list of terms related to the ambiguous word. This list is obtained using the distributional similarity method proposed by Lin Dekang to obtain a thesaurus. In the method of McCarthy et al., every occurrence of the ambiguous word uses the same thesaurus, regardless of the context where the ambiguous word occurs. Our method accounts for the context of a word when determining the sense of an ambiguous word by building the list of distributed similar words based on the syntactic context of the ambiguous word. We obtain a top precision of 77.54% of accuracy versus 67.10% of the original method tested on SemCor. We also analyze the effect of the number of weighted terms in the tasks of finding the Most Frecuent Sense (MFS) and WSD, and experiment with several corpora for building the Word Space Model.


[1] Schütze H. Dimensions of meaning. In Proc. ACM/IEEE Conference on Supercomputing (Supercomputing,1992), Mannheim, Germany, June, 1992, pp.787-796.

[2] Karlgren J, Sahlgren M. From Words to Understanding. Foundations of Real-World Intelligence, Stanford: CSLI Publications, 2001, pp.294-308.

[3] McCarthy D, Koeling R, Weeds J et al. Finding predominant word senses in untagged text. In Proc. the 42nd Annual Meeting of the Association for Computational Linguistics, Barcelona, Spain, 2004.

[4] Lin D. Automatic retrieval and clustering of similar words. In Proc. the 17th Int. Conf. Computational Linguistics, Montreal, Canada, Aug. 10-14, 1998, pp.768-774.

[5] Kilgarriff A, Rosenzweig J. English SENSEVAL: Report and results. In Proc. LREC, Athens, May-June 2000.

[6] Patwardhan S, Banerjee S, Pedersen T. Using measures of semantic relatedness for word sense disambiguation. In Proc. the Fourth International Conference on Intelligent Text Processing and Computational Linguistics, Mexico City, Mexico, 2003, pp.241-257.

[7] Sahlgren M. The Word-Space Model: Using distributional analysis to represent syntagmatic and paradigmatic relations between words in high-dimensional vector spaces
[Ph.D. Dissertation]. Department of Linguistics, Stockholm University, 2006.

[8] Lin D. Dependency-based evaluation of MINIPAR. In Proc. Workshop on the Evaluation of Parsing Systems at LREC, Granada, Spain, 1998, pp.317-330.

[9] Hays D. Dependency theory: A formalism and some observations. Language, 1964, 40(4): 511-525.

[10] Mel'cuk I A. Dependency Syntax: Theory and Practice. State University of New York Press, Albany, N.Y., 1987.

[11] Pedersen T, Patwardhan S, Michelizzi J. WordNet::Similarity: Measuring the relatedness of concepts. In Proc. the Nineteenth National Conference on Artificial Intelligence (AAAI-2004), San Jose, CA, 2004, pp.1024-1025.

[12] Miller G. Introduction to WordNet: An On-line Lexical Database. Princeton Univesity, 1993.

[13] Miller G. WordNet: An on-line lexical database. International Journal of Lexicography, 1990, 3(4): 235-244.

[14] Resnik P. Using information content to evaluate semantic similarity in a taxonomy. In Proc. the 14th International Joint Conference on Artificial Intelligence, Montreal, Canada, Aug. 20-25, 1995, pp.448-453.

[15] Jiang J J, Conrath D W. Semantic similarity based on corpus statistics and lexical taxonomy. In Proc. International Conference on Research in Computational Linguistics, Taiwan, China, Sept. 1997, pp.19-33. %statistics and lexical taxonomy. International Conference on Research

[16] Leacock C, Chodorow M. Combining Local Context and WordNet Similarity for Word Sense Identification. WordNet: An Electronic Lexical Database, Fellbaum C (ed.), 1998, pp.265-283.

[17] Tejada J, Gelbukh A, Calvo H. Unsupervised WSD with a dynamic thesaurus. In Proc. the 11th International Conference on Text, Speech and Dialogue (TSD 2008), Brno, Czech, Sept. 8-12, 2008, pp.201-210.

[18] Tejada J, Gelbukh A, Calvo H. An innovative two-stage WSD unsupervised method. SEPLN Journal, March 2008, 40: 99-105.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] Tai Juwei; Wang Jue; Chen Xin;. A Syntactic-Semantic Approach for Pattern Recognition and Knowledge Representation[J]. , 1988, 3(3): 161 -172 .
[2] Cai Shijie; Zhang Fuyan;. A Fast Algorithm for Polygon Operations[J]. , 1991, 6(1): 91 -96 .
[3] Zhang Bo; Zhang Ling;. A Relation Matrix Approach to Labelling Temporal Relations in Scheduling[J]. , 1991, 6(4): 339 -346 .
[4] Zhang Bo; Zhang Ling;. An Algorithm for Finding D-Time Table[J]. , 1992, 7(1): 62 -67 .
[5] Harald E. Otto;. UNDO, An Aid for Explorative Learning?[J]. , 1992, 7(3): 226 -236 .
[6] Shen Yidong;. Form alizing Incomplete Knowledge in Incomplete Databases[J]. , 1992, 7(4): 295 -304 .
[7] Zhao Zhaokeng; Dai Jun; Chen Wendan;. Automated Theorem Proving in Temporal Logic:T-Resolution[J]. , 1994, 9(1): 53 -62 .
[8] Yu Shengke;. Reasoning in H-Net: A Unified Approach to Intelligent Hypermedia Systems[J]. , 1996, 11(1): 83 -89 .
[9] Tian Zengping; Wang Yujun; Qu Yunyao; Shi Baile;. On the Expressive Power of F-Logic Language[J]. , 1997, 12(6): 510 -519 .
[10] Shuai Dianxun;. Concurrent Competitive Wave Approach to Hyper-Distributed Hyper-Parallel AI Processing[J]. , 1997, 12(6): 543 -554 .

ISSN 1000-9000(Print)

         1860-4749(Online)
CN 11-2296/TP

Home
Editorial Board
Author Guidelines
Subscription
Journal of Computer Science and Technology
Institute of Computing Technology, Chinese Academy of Sciences
P.O. Box 2704, Beijing 100190 P.R. China
Tel.:86-10-62610746
E-mail: jcst@ict.ac.cn
 
  Copyright ©2015 JCST, All Rights Reserved