A Decomposable Attention Model for Natural Language Inference
Ankur P. Parikha, Oscar Täckströma, Dipanjan Dasa, Jakob Uszkoreitb
- aGoogle New York, NY
- bGoogle Mountain View, CA
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
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.
TL;DRThis work proposes a simple neural architecture for natural language inference that uses attention to decompose the problem into subproblems that can be solved separately, thus making it trivially parallelizable. (Semantic Scholar)