{"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/dynamic-self-attention-computing-attention","title":"Dynamic Self-Attention : Computing Attention over Words Dynamically for Sentence Embedding","arxiv_id":"1808.07383","date":"2018-08-22","proceeding":null,"authors":["Deunsol Yoon","Dongbok Lee","SangKeun Lee"],"abstract":"In this paper, we propose Dynamic Self-Attention (DSA), a new self-attention\nmechanism for sentence embedding. We design DSA by modifying dynamic routing in\ncapsule network (Sabouretal.,2017) for natural language processing. DSA attends\nto informative words with a dynamic weight vector. We achieve new\nstate-of-the-art results among sentence encoding methods in Stanford Natural\nLanguage Inference (SNLI) dataset with the least number of parameters, while\nshowing comparative results in Stanford Sentiment Treebank (SST) dataset.","url_abs":"http://arxiv.org/abs/1808.07383v1","url_pdf":"http://arxiv.org/pdf/1808.07383v1.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":"dynamic-self-attention-computing-attention","repo_url":"https://github.com/dsindex/iclassifier","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embedding","task_name":"Sentence Embedding"},{"task_slug":"sentence-embedding-1","task_name":"Sentence-Embedding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"2400D Multiple-Dynamic Self-Attention Model","rank_in_archive_order":45,"of":98,"metrics":{"% Test Accuracy":"87.4","% Train Accuracy":"89.0","Parameters":"7.0m"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"600D Dynamic Self-Attention Model","rank_in_archive_order":50,"of":98,"metrics":{"% Test Accuracy":"86.8","% Train Accuracy":"87.3","Parameters":"2.1m"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.07383","atlas_url":"https://app.syntology.ai/?focus=1808.07383","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}