摘要: This paper summarizes the results of some experiments for finding effective features disambiguation Turkish verbs. Word sense is a current area investigation in which verbs have dominant role. Generally more senses than other types words average and detecting these may lead to improvements word types. In this we considered only syntactical that can be obtained from corpus tested by using famous machine learning algorithms. Keywords—Word disambiguation, feature selection. I. INTRODUCTION
参考文章(27)
David Yarowsky, William A. Gale, Kenneth W. Church, Work on Statistical Methods for Word Sense Disambiguation ,(1992)
Kemal Pala, Karel Christodoulakis, Stamou Sofia Oflazer, BALKANET: A Multilingual Semantic Network for Balkan Languages ,(2001)
Rebecca Bruce, Ted Pedersen, A new supervised learning algorithm for word sense disambiguation national conference on artificial intelligence. pp. 604- 609 ,(1997)
Claire Cardie, Automating Feature Set Selection for Case-Based Learning of Linguistic Knowledge empirical methods in natural language processing. ,(1996)
David Yarowsky, Hierarchical Decision Lists for Word Sense Disambiguation Computers and The Humanities. ,vol. 34, pp. 179- 186 ,(2000) , 10.1023/A:1002674829964
Janyce M. Wiebe, Rebecca F. Bruce, Decomposable modeling in natural language processing Computational Linguistics. ,vol. 25, pp. 195- 207 ,(1999) , 10.5555/973306.973308
Andrew W. Moore, Mary S. Lee, Efficient Algorithms for Minimizing Cross Validation Error Machine Learning Proceedings 1994. pp. 190- 198 ,(1994) , 10.1016/B978-1-55860-335-6.50031-3
Orhan Bilgin, Özlem Çetinoğlu, Kemal Oflazer, Building a wordnet for Turkish Romanian Academy. ,(2004)
John Zelle, Hwee Tou Ng, Corpus-Based Approaches to Semantic Interpretation in Natural Language Processing ,(1997)
German Rigau, Lluís Màrquez, Gerard Escudero, Naive Bayes and Exemplar-based approaches to Word Sense Disambiguation revisited european conference on artificial intelligence. pp. 421- 425 ,(2000)