A Decomposable Attention Model for Natural Language Inference

Ankur Parikh1, Oscar Täckström1, Dipanjan Das2, Jakob Uszkoreit3
1Google, 2Google Inc., 3Google, Inc.


Abstract

We propose a simple neural architecture for natural language inference. Our approach uses attention to decompose the problem into subproblems that can be solved separately, thus making it trivially parallelizable. On the Stanford Natural Language Inference (SNLI) dataset, we obtain state-of-the-art results with almost an order of magnitude fewer parameters than previous work and without relying on any word-order information. Adding intra-sentence attention that takes a minimum amount of order into account yields further improvements.