Open Access Open Access  Restricted Access Subscription or Fee Access

Trigram Based Word Sense Disambiguation Using Neural Network

P. Tamilselvi, S.K. Srivatsa

Abstract


This paper presents a method to solve word sense ambiguity using neural network. Most of the previous word sense disambiguation approaches were based on neural networks, having limitations due to their huge feature set size. Here, trigram method is adopted in three ways: pre-trigram (wr1r2 - ambiguous word (w) and immediate two right words (r1r2)), in-trigram (l1wr1 – immediate left word (l1), ambiguous word (w) and immediate right word (r1)) and post-trigram (l2l1w – immediate left two words (l2l1) and ambiguous word (w)). Three trigram features are treated as input for five different neural networks, defined with one hidden layer with hidden neurons ranging from two to twenty. The input model is extracted from Brown corpus. In this, the performances of the networks are compared using mean squared error (mse) values. Among all networks, in-trigram based pattern recognition neural network gives 78.15% of accuracy.

Keywords


In-Trigram, Neural Network, Post-Trigram, Pre-Trigram and Word Sense Disambiguation

Full Text:

PDF

References


A. Azzini, C. da Costa Pereira, M. Dragoni, and A. Tettamanzi. Evolving Neural Networks for Word Sense Disambiguation, HIS‟08, pages 332-337, LNCS, Springer, Septermber 2008.

Atwell, E, Transforming a Parsed Corpus into a Corpus Parser in Kyto, M, Ihalainen, O &Risanen, M (editors), Corpus Linguistics, Hard and Soft: Proceedings of the ICAME 8th International Conference on English Language Research on Computerised Corpora, pp 61-70, Rodopi, 1988.

Hinrich Schutze, Automatic word sense discrimination, Computation Linguistics, 24(1), pp.97-124, 1998.

Leech, G, Garside, R & Atwell, E, The Automatic Grammatical Tagging of the LOB Corpus ICAME Journal of the International Computer Archive of Modern English Vol.7, 1983.

Ng. H.T. and Zelle J Corpus-Based Approaches to Semantic Interpretation in Natural Language Processing. AI Magazine, 18(4), PP. 45-64, 1997,

Palmer, D. D. Tokenisation and sentence segmentation. In Dale, R.Somers, H. L., and Moisl, H. (Eds.), Handbook of Natural Language Processing. Marcel Dekker, Inc., New York, NY, USA, 2000

Michael Fleischman and Eduard Hovy. 2002. Fine grained classification of named entities. In Proceedings of ACL-2002, pages 1–7, Morristown, NJ, USA, 2002.

P.Tamilselvi, S.K.Srivatsa, (J) Part-Of-Speech Tag Assignment Using Hidden Markov Model, International Journal of Highly reliable Electronic System, Vol-3, No-2, pp 103-110, 2010.

Yarowsky. D, Word sense disambiguation using statistical models of Roget‟s categories trained on large corpora, In: Zampolli, A., ed. Computatuion Linguistic‟92. Nantas: Association for computational Linguistis, 454-460, 1992.

You-Jin Chung, Sin-Jae Kang, Kyong-Hi Moon and Jong-Hyeok Lee, "Word Sense Disambiguation in a Korean-to-Japanese MT System Using Neural Networks", COLING 2002 Workshop on Machine Translation in Asia, pp. 74-80, 2002.

Zhimao Lu, Ting Liu, and Sheng Li. Combining neural networks and statistics for chinese word sense disambiguation. In Oliver Streiter and Qin Lu, editors, ACL SIGHAN Workshop,pages 49-56, 2004.

P.Tamilselvi, S.K.Srivatsa, Decentralized E-Dictionary (DED) for NLP task, Proceedings of ICMCS-09, International conference on Mathematics and computer Science, India, 2009.

P.Tamilselvi, S.K.Srivatsa, (C) A Study on Lexicographical Information using open source lexical databases, Proceeding of NCRTCSE-10, National conference on Recent Trends in Computer Science and Engineering, 2010.

C. Fellbaum. WordNet: An Electronic Lexical Database. MIT Press, Cambridge, Massachusetts, 1998.

Massimiliano Ciaramita, Thomas Hofmann, and Mark Johnson, Hierarchical semantic classification: Word sense disambiguation with world knowledge. In The 18th International Joint Conference on Artificial Intelligence, Acapulco, Mexico, 2003.


Refbacks

  • There are currently no refbacks.