Papers › Enhanced LSTM for Natural Language Inference

Enhanced LSTM for Natural Language Inference

20 Sep 2016ACL 2017 7arXiv:1609.06038archive 2025-07-28

Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Si Wei, Hui Jiang, Diana Inkpen

Reasoning and inference are central to human and artificial intelligence. Modeling inference in human language is very challenging. With the availability of large annotated data (Bowman et al., 2015), it has recently become feasible to train neural network based inference models, which have shown to be very effective. In this paper, we present a new state-of-the-art result, achieving the accuracy of 88.6% on the Stanford Natural Language Inference Dataset. Unlike the previous top models that use very complicated network architectures, we first demonstrate that carefully designing sequential inference models based on chain LSTMs can outperform all previous models. Based on this, we further show that by explicitly considering recursive architectures in both local inference modeling and inference composition, we achieve additional improvement. Particularly, incorporating syntactic parsing information contributes to our best result---it further improves the performance even when added to the already very strong model.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

lukecq1231/nli officialmentioned in paperApache-2.0 report
Coda-s/BJTU_NLP_Practice mentioned on GitHubpytorch report
HuihuiChyan/BJTUNLP_Practice2020 mentioned on GitHubpytorch report
HuihuiChyan/BJTUNLP_Practice2021 mentioned on GitHubpytorch report
SJHBXShub/Question_pair mentioned on GitHubtf report
blcunlp/CNLI mentioned on GitHubtf report
coetaur0/ESIM mentioned on GitHubpytorchApache-2.0 report
nyu-mll/multiNLI mentioned on GitHubtf report
thomasdic2000/enhancedLSTM 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 600D ESIM + 300D Syntactic TreeLSTM % Test Accuracy 88.6 #33 of 98 Archive leaderboard report
Natural Language Inference SNLI 600D ESIM + 300D Syntactic TreeLSTM % Train Accuracy 93.5 #33 of 98 Archive leaderboard report
Natural Language Inference SNLI 600D ESIM + 300D Syntactic TreeLSTM Parameters 7.7m #33 of 98 Archive leaderboard report
Natural Language Inference SNLI Enhanced Sequential Inference Model (Chen et al., [2017a]) % Test Accuracy 88.0 #41 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.

Methods

Introduced by this paper: ESIM

ESIM

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