Deep Fusion Lstms For Text Semantic Matching
PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1(2016)
摘要
Recently, there is rising interest in modelling the interactions of text pair with deep neural networks. In this paper, we propose a model of deep fusion LSTMs (DF-LSTMs) to model the strong interaction of text pair in a recursive matching way. Specifically, DF-LSTMs consist of two interdependent LSTMs, each of which models a sequence under the influence of another. We also use external memory to increase the capacity of LSTMs, thereby possibly capturing more complicated matching patterns. Experiments on two very large datasets demonstrate the efficacy of our proposed architecture. Furthermore, we present an elaborate qualitative analysis of our models, giving an intuitive understanding how our model worked.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络