{"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/joint-slot-filling-and-intent-detection-via","title":"Joint Slot Filling and Intent Detection via Capsule Neural Networks","arxiv_id":"1812.09471","date":"2018-12-22","proceeding":"ACL 2019 7","authors":["Chenwei Zhang","Yaliang Li","Nan Du","Wei Fan","Philip S. Yu"],"abstract":"Being able to recognize words as slots and detect the intent of an utterance has been a keen issue in natural language understanding. The existing works either treat slot filling and intent detection separately in a pipeline manner, or adopt joint models which sequentially label slots while summarizing the utterance-level intent without explicitly preserving the hierarchical relationship among words, slots, and intents. To exploit the semantic hierarchy for effective modeling, we propose a capsule-based neural network model which accomplishes slot filling and intent detection via a dynamic routing-by-agreement schema. A re-routing schema is proposed to further synergize the slot filling performance using the inferred intent representation. Experiments on two real-world datasets show the effectiveness of our model when compared with other alternative model architectures, as well as existing natural language understanding services.","url_abs":"https://arxiv.org/abs/1812.09471v2","url_pdf":"https://arxiv.org/pdf/1812.09471v2.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":"joint-slot-filling-and-intent-detection-via","repo_url":"https://github.com/czhang99/Capsule-NLU","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"joint-slot-filling-and-intent-detection-via","repo_url":"https://github.com/Fireblossom/DeepDarkHomeword","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"joint-slot-filling-and-intent-detection-via","repo_url":"https://github.com/Fireblossom/DeepDarkHomework","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"intent-detection","task_name":"Intent Detection"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"slot-filling","task_name":"Slot Filling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/intent-detection-on-atis","task":"Intent Detection","dataset":"ATIS","model":"Capsule-NLU","rank_in_archive_order":16,"of":16,"metrics":{"Accuracy":"0.95"},"uses_additional_data":false},{"leaderboard":"/sota/intent-detection-on-snips","task":"Intent Detection","dataset":"SNIPS","model":"Capsule-NLU","rank_in_archive_order":9,"of":10,"metrics":{"Accuracy":"97.3"},"uses_additional_data":false},{"leaderboard":"/sota/slot-filling-on-atis","task":"Slot Filling","dataset":"ATIS","model":"Capsule-NLU","rank_in_archive_order":11,"of":14,"metrics":{"F1":"0.952"},"uses_additional_data":false},{"leaderboard":"/sota/slot-filling-on-snips","task":"Slot Filling","dataset":"SNIPS","model":"Capsule-NLU","rank_in_archive_order":9,"of":10,"metrics":{"F1":"0.918"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1812.09471","atlas_url":"https://app.syntology.ai/?focus=1812.09471","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}