TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Natural Language Inference	SNLI	Stochastic Answer Network	% Test Accuracy	88.5	# 32
Natural Language Inference	SNLI	Stochastic Answer Network	% Train Accuracy	93.3	# 22
Natural Language Inference	SNLI	Stochastic Answer Network	Parameters	3.5m	# 4

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

Stochastic Answer Networks for Natural Language Inference

21 Apr 2018 · Xiaodong Liu, Kevin Duh, Jianfeng Gao ·

We propose a stochastic answer network (SAN) to explore multi-step inference strategies in Natural Language Inference. Rather than directly predicting the results given the inputs, the model maintains a state and iteratively refines its predictions. Our experiments show that SAN achieves the state-of-the-art results on three benchmarks: Stanford Natural Language Inference (SNLI) dataset, MultiGenre Natural Language Inference (MultiNLI) dataset and Quora Question Pairs dataset.

PDF Abstract