Abstract:For vocabulary ambiguity problem in Chinese

CNN(Convolution Neural Network) is adopted to determine true meaning of ambiguousvocabulary where word

part of speech and translation around its left and rightadjacent words are used. We select disambiguation window of ambiguous wordwhich contains two adjacent lexical units and word

partofspeech andtranslation are extracted as disambiguation features Based on disambiguationfeatures

convolution neural network is used to construct word sense disambiguation(WSD) classifier Training corpus in SemEval-2007: Task#5 and semanticannotation corpus in Harbin Institute of Technology are used to optimizeparameters of CNN Test corpus in SemEval-2007: Task#5 is applied to test wordsense disambiguation classifier Experimental results show that compared withBayes model and BP neural network

the proposed method in this paper can makeaverage disambiguation accuracy improve 14.94% and 6.9%