Papers › Dynamic Self-Attention : Computing Attention over Words Dynamically for Sentence Embedding

Dynamic Self-Attention : Computing Attention over Words Dynamically for Sentence Embedding

22 Aug 2018arXiv:1808.07383archive 2025-07-28

Deunsol Yoon, Dongbok Lee, SangKeun Lee

In this paper, we propose Dynamic Self-Attention (DSA), a new self-attention mechanism for sentence embedding. We design DSA by modifying dynamic routing in capsule network (Sabouretal.,2017) for natural language processing. DSA attends to informative words with a dynamic weight vector. We achieve new state-of-the-art results among sentence encoding methods in Stanford Natural Language Inference (SNLI) dataset with the least number of parameters, while showing comparative results in Stanford Sentiment Treebank (SST) dataset.

PaperPDFCode

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

Code

dsindex/iclassifier 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 InferenceSentenceSentence EmbeddingSentence-Embedding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Natural Language Inference SNLI 2400D Multiple-Dynamic Self-Attention Model % Test Accuracy 87.4 #45 of 98 Archive leaderboard report
Natural Language Inference SNLI 2400D Multiple-Dynamic Self-Attention Model % Train Accuracy 89.0 #45 of 98 Archive leaderboard report
Natural Language Inference SNLI 2400D Multiple-Dynamic Self-Attention Model Parameters 7.0m #45 of 98 Archive leaderboard report
Natural Language Inference SNLI 600D Dynamic Self-Attention Model % Test Accuracy 86.8 #50 of 98 Archive leaderboard report
Natural Language Inference SNLI 600D Dynamic Self-Attention Model % Train Accuracy 87.3 #50 of 98 Archive leaderboard report
Natural Language Inference SNLI 600D Dynamic Self-Attention Model Parameters 2.1m #50 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