%0 Journal Article
%T 一种基于Tree-LSTM的句子相似度计算方法<br>An Approach of Sentence Similarity on Tree-LSTM
%A 杨萌
%A 李培峰
%A 朱巧明
%J 北京大学学报（自然科学版）
%D 2018
%R 10.13209/j.0479-8023.2017.169
%X 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。<br>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.
%K 句子相似度计算
%K Tree-LSTM
%K 结构化特征&lt
%K br&gt
%K sentence similarity computation
%K Tree-LSTM
%K structural representations
%U http://xbna.pku.edu.cn/CN/abstract/abstract3213.shtml