Papers › Sentence Embeddings in NLI with Iterative Refinement Encoders

Sentence Embeddings in NLI with Iterative Refinement Encoders

27 Aug 2018arXiv:1808.08762archive 2025-07-28

Aarne Talman, Anssi Yli-Jyrä, Jörg Tiedemann

Sentence-level representations are necessary for various NLP tasks. Recurrent neural networks have proven to be very effective in learning distributed representations and can be trained efficiently on natural language inference tasks. We build on top of one such model and propose a hierarchy of BiLSTM and max pooling layers that implements an iterative refinement strategy and yields state of the art results on the SciTail dataset as well as strong results for SNLI and MultiNLI. We can show that the sentence embeddings learned in this way can be utilized in a wide variety of transfer learning tasks, outperforming InferSent on 7 out of 10 and SkipThought on 8 out of 9 SentEval sentence embedding evaluation tasks. Furthermore, our model beats the InferSent model in 8 out of 10 recently published SentEval probing tasks designed to evaluate sentence embeddings' ability to capture some of the important linguistic properties of sentences.

Paper PDF Code

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

Code

Helsinki-NLP/HBMP officialmentioned in papermentioned 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 Sentence Sentence Embedding Sentence Embeddings Sentence-Embedding Transfer Learning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Natural Language Inference	SNLI	600D Hierarchical BiLSTM with Max Pooling (HBMP, code)	% Test Accuracy	86.6	#54 of 98	Archive leaderboard	report
Natural Language Inference	SNLI	600D Hierarchical BiLSTM with Max Pooling (HBMP, code)	% Train Accuracy	89.9	#54 of 98	Archive leaderboard	report
Natural Language Inference	SNLI	600D Hierarchical BiLSTM with Max Pooling (HBMP, code)	Parameters	22m	#54 of 98	Archive leaderboard	report
Natural Language Inference	SciTail	Hierarchical BiLSTM Max Pooling	Accuracy	86.0	#5 of 13	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

BiLSTM HBMP LSTM Max Pooling Sigmoid Activation Tanh Activation

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