Thai Language Sentence Similarity Computation Based on Syntactic Structure and Semantic Vector

2017 International Symposium on Application of Materials Science and Energy Materials

材料科学;能源学

Wang, Hongbin^1 ; Feng, Yinhan^1 ; Cheng, Liang^2

Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming

650504, China^1

City College, Kunming University of Science and Technology, Kunming

650051, China^2

关键词: Chinese language;    Machine translations;    Part Of Speech;    Question answering systems;    Semantic similarity;    Semantic vectors;    Sentence similarity;    Syntactic structure;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/322/5/052011/pdf
DOI  :  10.1088/1757-899X/322/5/052011

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

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.