Papers › Multiway Attention Networks for Modeling Sentence Pairs

Multiway Attention Networks for Modeling Sentence Pairs

1 Jul 2018IJCAI 2018 7archive 2025-07-28

Chuanqi Tan, Furu Wei, Wenhui Wang, Weifeng Lv, Ming Zhou

Modeling sentence pairs plays the vital role for judging the relationship between two sentences, such as paraphrase identification, natural language inference, and answer sentence selection. Previous work achieves very promising results using neural networks with attention mechanism. In this paper, we propose the multiway attention networks which employ multiple attention functions to match sentence pairs under the matching-aggregation framework. Specifically, we design four attention functions to match words in corresponding sentences. Then, we aggregate the matching information from each function, and combine the information from all functions to obtain the final representation. Experimental results demonstrate that the proposed multiway attention networks improve the result on the Quora Question Pairs, SNLI, MultiNLI, and answer sentence selection task on the SQuAD dataset.

PaperPDFCode

Code

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 InferenceParaphrase IdentificationSentence

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Natural Language Inference SNLI 150D Multiway Attention Network Ensemble % Test Accuracy 89.4 #18 of 98 Archive leaderboard report
Natural Language Inference SNLI 150D Multiway Attention Network Ensemble % Train Accuracy 95.5 #18 of 98 Archive leaderboard report
Natural Language Inference SNLI 150D Multiway Attention Network Ensemble Parameters 58m #18 of 98 Archive leaderboard report
Natural Language Inference SNLI 150D Multiway Attention Network % Test Accuracy 88.3 #37 of 98 Archive leaderboard report
Natural Language Inference SNLI 150D Multiway Attention Network % Train Accuracy 94.5 #37 of 98 Archive leaderboard report
Natural Language Inference SNLI 150D Multiway Attention Network Parameters 14m #37 of 98 Archive leaderboard report
Paraphrase Identification Quora Question Pairs MwAN Accuracy 89.12 #19 of 31 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