Papers › Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications

Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications

6 Jun 2019ACL 2019 7arXiv:1906.02829archive 2025-07-28

Wei Zhao, Haiyun Peng, Steffen Eger, Erik Cambria, Min Yang

Obstacles hindering the development of capsule networks for challenging NLP applications include poor scalability to large output spaces and less reliable routing processes. In this paper, we introduce: 1) an agreement score to evaluate the performance of routing processes at instance level; 2) an adaptive optimizer to enhance the reliability of routing; 3) capsule compression and partial routing to improve the scalability of capsule networks. We validate our approach on two NLP tasks, namely: multi-label text classification and question answering. Experimental results show that our approach considerably improves over strong competitors on both tasks. In addition, we gain the best results in low-resource settings with few training instances.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

AIPHES/acl19-generalization-capsule mentioned on GitHubpytorch report
andyweizhao/NLP-Capsule mentioned on GitHubpytorch report
andyweizhao/capsule mentioned on GitHubtf report
kevindeangeli/capsuleNetwork mentioned on GitHubtf 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

General ClassificationMulti-Label Text ClassificationQuestion AnsweringText Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Label Text Classification EUR-Lex NLP-Cap P@1 80.2 #2 of 3 Archive leaderboard report
Multi-Label Text Classification EUR-Lex NLP-Cap P@3 65.48 #2 of 3 Archive leaderboard report
Multi-Label Text Classification EUR-Lex NLP-Cap P@5 52.83 #2 of 3 Archive leaderboard report
Multi-Label Text Classification EUR-Lex NLP-Cap nDCG@1 80.2 #2 of 3 Archive leaderboard report
Multi-Label Text Classification EUR-Lex NLP-Cap nDCG@3 71.11 #2 of 3 Archive leaderboard report
Multi-Label Text Classification EUR-Lex NLP-Cap nDCG@5 68.8 #2 of 3 Archive leaderboard report
Question Answering TrecQA NLP-Capsule MAP 0.7773 #9 of 13 Archive leaderboard report
Question Answering TrecQA NLP-Capsule MRR 0.7416 #9 of 13 Archive leaderboard report
Text Classification RCV1 NLP-Cap P@1 97.05 #4 of 4 Archive leaderboard report
Text Classification RCV1 NLP-Cap P@3 81.27 #4 of 4 Archive leaderboard report
Text Classification RCV1 NLP-Cap P@5 56.33 #4 of 4 Archive leaderboard report
Text Classification RCV1 NLP-Cap nDCG@1 97.05 #4 of 4 Archive leaderboard report
Text Classification RCV1 NLP-Cap nDCG@3 92.47 #4 of 4 Archive leaderboard report
Text Classification RCV1 NLP-Cap nDCG@5 93.11 #4 of 4 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