A Decomposable Attention Model for Natural Language Inference
2016pp. 2249–2255
Citations Over TimeTop 1% of 2016 papers
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.
Related Papers
- → DeepSpeed- Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale(2022)208 cited
- → The Role of Consumers' Intuitions in Inference Making(1994)216 cited
- → POSITIVE-NEGATIVE ASYMMETRY IN MENTAL STATE INFERENCE: REPLICATION AND EXTENSION(2006)1 cited
- On the Probable Inference in Criminal Investigation(2004)
- → INFLUENCE OF RELIEF ON ANTHROPOGENIC LOADING OF NATURAL LANDSCAPES (ON THE EXAMPLE OF LANKARAN NATURAL REGION OF AZERBAIJAN)(2022)