What does this research mean for the field?

Q: What does this research mean for the field?

The TBCNNpair model, which combines tree-based convolutional neural networks for semantic extraction with heuristic matching layers, significantly outperforms existing sentence encoding-based approaches in recognizing natural language entailment and contradiction. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

January 1, 2016Open Access

Natural Language Inference by Tree-Based Convolution and Heuristic Matching

Key Points

Key points are not available for this paper at this time.

Abstract

In this paper, we propose the TBCNNpair model to recognize entailment and contradiction between two sentences. In our model, a tree-based convolutional neural network (TBCNN) captures sentencelevel 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.

Bookmark

View Full Paper