A Decomposable Attention Model for Natural Language Inference
2016-06-06EMNLP 2016Code Available1· sign in to hype
Ankur P. Parikh, Oscar Täckström, Dipanjan Das, Jakob Uszkoreit
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/bitextor/bicleaner-aitf★ 40
- github.com/fatma-mohamed-98/Recognising-Textual-Entailment-using-Decomposable-Attentionnone★ 0
- github.com/sminer3/duplicate_statement_detectionnone★ 0
- github.com/DeNeutoy/Decomposable_Attntf★ 0
- github.com/libowen2121/SNLI-decomposable-attentionpytorch★ 0
- github.com/sunsiqi26/Entailment-with-TensorFlowtf★ 0
- github.com/blcunlp/CNLItf★ 0
- github.com/harvardnlp/decomp-attnnone★ 0
- github.com/nvnhat95/Natural-Language-Inferencepytorch★ 0
- github.com/dmlc/gluon-nlpmxnet★ 0
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| SNLI | 200D decomposable attention feed-forward model with intra-sentence attention | % Test Accuracy | 86.8 | — | Unverified |
| SNLI | 200D decomposable attention model with intra-sentence attention | % Test Accuracy | 86.8 | — | Unverified |
| SNLI | 200D decomposable attention feed-forward model | % Test Accuracy | 86.3 | — | Unverified |
| SNLI | 200D decomposable attention model | % Test Accuracy | 86.3 | — | Unverified |