Sentence Similarity on Structural Representations

摘要：

　　Most previous approaches used various kinds of plain similarity features to represent the similarity of a sentence pair,and one of its limitations is its weak representation ability.This paper introduces the relational structures representation(shallow syntactic tree,dependency tree)to compute sentence similarity.Experimental results manifest that our approach achieves higher performance than that only uses plain features.

关键词： Sentence Similarity Structural Representations Shallow Syntactic Tree Dependency Tree

作者: YANG Meng LI Peifeng ZHU Qiaoming

作者单位: Natural Language Processing Lab,Soochow University,Suzhou 215006;School of Computer Science and Technology,Soochow University,Suzhou 215006

会议类型: 国际会议

会议名称: 第五届自然语言处理与中文计算会议(NLPCC-ICCPOL2016)

会议地点: 昆明

会议语种:英文

页码: 1-10

在线出版日期: 2016-12-02（万方平台首次上网日期，不代表论文的发表时间）