Papers › Stochastic Answer Networks for Natural Language Inference

Stochastic Answer Networks for Natural Language Inference

21 Apr 2018arXiv:1804.07888archive 2025-07-28

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Xaniar87/SAN_SQuAD2 mentioned on GitHubpytorch report
kevinduh/san_mrc mentioned on GitHubpytorch report
yongbowin/san_mrc_annotation mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Natural Language Inference

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Natural Language Inference SNLI Stochastic Answer Network % Test Accuracy 88.5 #35 of 98 Archive leaderboard report
Natural Language Inference SNLI Stochastic Answer Network % Train Accuracy 93.3 #35 of 98 Archive leaderboard report
Natural Language Inference SNLI Stochastic Answer Network Parameters 3.5m #35 of 98 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections