Thai Language Sentence Similarity Computation Based on Syntactic Structure and Semantic Vector
Sentence similarity computation plays an increasingly important role in text mining,Web page retrieval,machine translation,speech recognition and question answering systems.Thai language as a kind of resources scarce language,it is not like Chinese language with HowNet and CiLin resources.So the Thai sentence similarity research faces some challenges.In order to solve this problem of the Thai language sentence similarity computation.This paper proposes a novel method to compute the similarity of Thai language sentence based on syntactic structure and semantic vector.This method firstly uses the Part-of-Speech(POS)dependency to calculate two sentences syntactic structure similarity,and then through the word vector to calculate two sentences semantic similarity.Finally,we combine the two methods to calculate two Thai language sentences similarity.The proposed method not only considers semantic,but also considers the sentence syntactic structure.The experiment result shows that this method in Thai language sentence similarity computation is feasible.
Hongbin Wang Yinhan Feng Liang Cheng
Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunmi City College,Kunming University of Science and Technology,Kunming,650051,China
国际会议
上海
英文
1-9
2017-12-28（万方平台首次上网日期，不代表论文的发表时间）