Papers › Shortcut-Stacked Sentence Encoders for Multi-Domain Inference

Shortcut-Stacked Sentence Encoders for Multi-Domain Inference

7 Aug 2017WS 2017 9arXiv:1708.02312archive 2025-07-28

Yixin Nie, Mohit Bansal

We present a simple sequential sentence encoder for multi-domain natural language inference. Our encoder is based on stacked bidirectional LSTM-RNNs with shortcut connections and fine-tuning of word embeddings. The overall supervised model uses the above encoder to encode two input sentences into two vectors, and then uses a classifier over the vector combination to label the relationship between these two sentences as that of entailment, contradiction, or neural. Our Shortcut-Stacked sentence encoders achieve strong improvements over existing encoders on matched and mismatched multi-domain natural language inference (top non-ensemble single-model result in the EMNLP RepEval 2017 Shared Task (Nangia et al., 2017)). Moreover, they achieve the new state-of-the-art encoding result on the original SNLI dataset (Bowman et al., 2015).

PaperPDFConference PDFCode

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

Code

easonnie/multiNLI_encoder officialmentioned in papermentioned on GitHubpytorch report
DorinK/Implementing-an-SNLI-Paper 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 InferenceSentenceWord Embeddings

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Natural Language Inference SNLI 600D Residual stacked encoders % Test Accuracy 86.0 #63 of 98 Archive leaderboard report
Natural Language Inference SNLI 600D Residual stacked encoders % Train Accuracy 91.0 #63 of 98 Archive leaderboard report
Natural Language Inference SNLI 600D Residual stacked encoders Parameters 29m #63 of 98 Archive leaderboard report
Natural Language Inference SNLI 300D Residual stacked encoders % Test Accuracy 85.7 #67 of 98 Archive leaderboard report
Natural Language Inference SNLI 300D Residual stacked encoders % Train Accuracy 89.8 #67 of 98 Archive leaderboard report
Natural Language Inference SNLI 300D Residual stacked encoders Parameters 9.7m #67 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