{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/towards-scalable-and-reliable-capsule","title":"Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications","arxiv_id":"1906.02829","date":"2019-06-06","proceeding":"ACL 2019 7","authors":["Wei Zhao","Haiyun Peng","Steffen Eger","Erik Cambria","Min Yang"],"abstract":"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.","url_abs":"https://arxiv.org/abs/1906.02829v1","url_pdf":"https://arxiv.org/pdf/1906.02829v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"towards-scalable-and-reliable-capsule","repo_url":"https://github.com/AIPHES/acl19-generalization-capsule","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"towards-scalable-and-reliable-capsule","repo_url":"https://github.com/andyweizhao/NLP-Capsule","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"towards-scalable-and-reliable-capsule","repo_url":"https://github.com/andyweizhao/capsule","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"towards-scalable-and-reliable-capsule","repo_url":"https://github.com/andyweizhao/capsule_text_classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"towards-scalable-and-reliable-capsule","repo_url":"https://github.com/kevindeangeli/capsuleNetwork","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"multi-label-text-classification","task_name":"Multi-Label Text Classification"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"text-classification","task_name":"Text Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-label-text-classification-on-eur-lex","task":"Multi-Label Text Classification","dataset":"EUR-Lex","model":"NLP-Cap","rank_in_archive_order":2,"of":3,"metrics":{"P@1":"80.2","P@3":"65.48","P@5":"52.83","nDCG@1":"80.2","nDCG@3":"71.11","nDCG@5":"68.8"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-trecqa","task":"Question Answering","dataset":"TrecQA","model":"NLP-Capsule","rank_in_archive_order":9,"of":13,"metrics":{"MAP":"0.7773","MRR":"0.7416"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-rcv1","task":"Text Classification","dataset":"RCV1","model":"NLP-Cap","rank_in_archive_order":4,"of":4,"metrics":{"P@1":"97.05","P@3":"81.27","P@5":"56.33","nDCG@1":"97.05","nDCG@3":"92.47","nDCG@5":"93.11"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1906.02829","atlas_url":"https://app.syntology.ai/?focus=1906.02829","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}