TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Natural Language Inference	SNLI	200D decomposable attention model with intra-sentence attention	% Test Accuracy	86.8	# 48
Natural Language Inference	SNLI	200D decomposable attention model with intra-sentence attention	% Train Accuracy	90.5	# 44
Natural Language Inference	SNLI	200D decomposable attention model with intra-sentence attention	Parameters	580k	# 4
Natural Language Inference	SNLI	200D decomposable attention model	% Test Accuracy	86.3	# 56
Natural Language Inference	SNLI	200D decomposable attention model	% Train Accuracy	89.5	# 50
Natural Language Inference	SNLI	200D decomposable attention model	Parameters	380k	# 4

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/a-decomposable-attention-model-for-natural/natural-language-inference-on-snli)](https://paperswithcode.com/sota/natural-language-inference-on-snli?p=a-decomposable-attention-model-for-natural)`

A Decomposable Attention Model for Natural Language Inference

EMNLP 2016 · Ankur P. Parikh, Oscar Täckström, Dipanjan Das, Jakob Uszkoreit ·

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.

PDF Abstract EMNLP 2016 PDF EMNLP 2016 Abstract

Code

Add Remove Mark official

dmlc/gluon-nlp

2,548

harvardnlp/decomp-attn

libowen2121/SNLI-decomposable-atten…

blcunlp/CNLI

bitextor/bicleaner-ai

See all 10 implementations

Tasks

Add Remove

Natural Language Inference

Sentence

Datasets

SNLI

Results from the Paper

Edit

Ranked #47 on Natural Language Inference on SNLI

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Natural Language Inference	SNLI	200D decomposable attention model with intra-sentence attention	% Test Accuracy	86.8	# 48	Compare
			% Train Accuracy	90.5	# 44	Compare
			Parameters	580k	# 4	Compare
Natural Language Inference	SNLI	200D decomposable attention model	% Test Accuracy	86.3	# 56	Compare
			% Train Accuracy	89.5	# 50	Compare
			Parameters	380k	# 4	Compare

Methods

Add Remove

No methods listed for this paper. Add relevant methods here

Edit Social Preview

A Decomposable Attention Model for Natural Language Inference

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove