# Stochastic Answer Networks for Natural Language Inference

arXiv: https://arxiv.org/abs/1804.07888 · HTML: https://mlsanity.com/paper/1804.07888/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2018.

## Built on by (most cited first, 2 of 2)

- [Towards Robust Ranker for Text Retrieval](https://mlsanity.com/paper/2206.08063/) (2022)
- [SILT: Efficient transformer training for inter-lingual inference](https://mlsanity.com/paper/2103.09635/) (2021)

## Abstract (arXiv)

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.