Papers › Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention

Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention

30 May 2016arXiv:1605.09090archive 2025-07-28

Yang Liu, Chengjie Sun, Lei Lin, Xiaolong Wang

In this paper, we proposed a sentence encoding-based model for recognizing text entailment. In our approach, the encoding of sentence is a two-stage process. Firstly, average pooling was used over word-level bidirectional LSTM (biLSTM) to generate a first-stage sentence representation. Secondly, attention mechanism was employed to replace average pooling on the same sentence for better representations. Instead of using target sentence to attend words in source sentence, we utilized the sentence's first-stage representation to attend words appeared in itself, which is called "Inner-Attention" in our paper . Experiments conducted on Stanford Natural Language Inference (SNLI) Corpus has proved the effectiveness of "Inner-Attention" mechanism. With less number of parameters, our model outperformed the existing best sentence encoding-based approach by a large margin.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Smerity/keras_snli mentioned on GitHubSyntology: not harvested report
songyang0716/NLP pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A large annotated corpus for learning natural language inference (arXiv:1508.05326; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Natural Language InferenceSentence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Natural Language Inference SNLI 600D (300+300) BiLSTM encoders with intra-attention and symbolic preproc. % Test Accuracy 85.0 #74 of 98 Archive leaderboard report
Natural Language Inference SNLI 600D (300+300) BiLSTM encoders with intra-attention and symbolic preproc. % Train Accuracy 85.9 #74 of 98 Archive leaderboard report
Natural Language Inference SNLI 600D (300+300) BiLSTM encoders with intra-attention and symbolic preproc. Parameters 2.8m #74 of 98 Archive leaderboard report
Natural Language Inference SNLI 600D (300+300) BiLSTM encoders with intra-attention % Test Accuracy 84.2 #81 of 98 Archive leaderboard report
Natural Language Inference SNLI 600D (300+300) BiLSTM encoders with intra-attention % Train Accuracy 84.5 #81 of 98 Archive leaderboard report
Natural Language Inference SNLI 600D (300+300) BiLSTM encoders with intra-attention Parameters 2.8m #81 of 98 Archive leaderboard report
Natural Language Inference SNLI 600D (300+300) BiLSTM encoders % Test Accuracy 83.3 #85 of 98 Archive leaderboard report
Natural Language Inference SNLI 600D (300+300) BiLSTM encoders % Train Accuracy 86.4 #85 of 98 Archive leaderboard report
Natural Language Inference SNLI 600D (300+300) BiLSTM encoders Parameters 2.0m #85 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

Average Pooling

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