A Decomposable Attention Model for Natural Language Inference
This work addresses efficient and accurate natural language inference for NLP applications, offering a novel method that is trivially parallelizable.
The authors tackled natural language inference by proposing a decomposable attention model that achieves state-of-the-art results on the SNLI dataset with significantly fewer parameters and minimal word-order information.
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.