English

Natural Language Inference by Tree-Based Convolution and Heuristic Matching

Computation and Language 2016-05-16 v3 Machine Learning

Abstract

In this paper, we propose the TBCNN-pair model to recognize entailment and contradiction between two sentences. In our model, a tree-based convolutional neural network (TBCNN) captures sentence-level semantics; then heuristic matching layers like concatenation, element-wise product/difference combine the information in individual sentences. Experimental results show that our model outperforms existing sentence encoding-based approaches by a large margin.

Keywords

Cite

@article{arxiv.1512.08422,
  title  = {Natural Language Inference by Tree-Based Convolution and Heuristic Matching},
  author = {Lili Mou and Rui Men and Ge Li and Yan Xu and Lu Zhang and Rui Yan and Zhi Jin},
  journal= {arXiv preprint arXiv:1512.08422},
  year   = {2016}
}

Comments

Accepted by ACL'16 as a short paper

R2 v1 2026-06-22T12:18:56.647Z