Acta Scientiarum Naturalium Universitatis Pekinensis ›› 2018, Vol. 54 ›› Issue (3): 481-486.DOI: 10.13209/j.0479-8023.2017.169

Previous Articles     Next Articles

An Approach of Sentence Similarity on Tree-LSTM

YANG Meng, LI Peifeng, ZHU Qiaoming   

  1. Department of Computer Science and Technology, Suchow University, Suzhou 215006
  • Received:2017-07-18 Revised:2017-11-24 Online:2018-05-20 Published:2018-05-20
  • Contact: LI Peifeng, E-mail: pfli(at)suda.edu.cn

一种基于Tree-LSTM的句子相似度计算方法

杨萌, 李培峰, 朱巧明   

  1. 苏州大学计算机科学与技术学院, 苏州 215006
  • 通讯作者: 李培峰, E-mail: pfli(at)suda.edu.cn
  • 基金资助:
    国家自然科学基金(61472265, 61772354)资助

Abstract:

Based on the shallow tree and dependency tree, the authors introduce the structural representations, NPST (new phrase-based shallow tree) and NPDT (new phrase-based dependency tree) to Tree-LSTM to compute sentence similarity. Experimental results manifest that the proposed approach achieves a higher performance than the baseline.

Key words: sentence similarity computation, Tree-LSTM, structural representations

摘要:

在浅层句法树和依存关系树的基础上, 提出两种结构化特征: 基于短语的浅层句法树NPST和基于短语的依存树NPDT, 并将它们与Tree-LSTM模型相结合, 进行句子相似度计算。实验表明, 使用结构化特征和Tree-LSTM会带来性能的提升。

关键词: 句子相似度计算, Tree-LSTM, 结构化特征

CLC Number: