English

Stochastic Answer Networks for Natural Language Inference

Computation and Language 2019-04-02 v2

Abstract

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.

Keywords

Cite

@article{arxiv.1804.07888,
  title  = {Stochastic Answer Networks for Natural Language Inference},
  author = {Xiaodong Liu and Kevin Duh and Jianfeng Gao},
  journal= {arXiv preprint arXiv:1804.07888},
  year   = {2019}
}

Comments

6 pages, 1 figures

R2 v1 2026-06-23T01:30:48.164Z