{"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/zero-shot-user-intent-detection-via-capsule","title":"Zero-shot User Intent Detection via Capsule Neural Networks","arxiv_id":"1809.00385","date":"2018-09-02","proceeding":"EMNLP 2018 10","authors":["Congying Xia","Chenwei Zhang","Xiaohui Yan","Yi Chang","Philip S. Yu"],"abstract":"User intent detection plays a critical role in question-answering and dialog\nsystems. Most previous works treat intent detection as a classification problem\nwhere utterances are labeled with predefined intents. However, it is\nlabor-intensive and time-consuming to label users' utterances as intents are\ndiversely expressed and novel intents will continually be involved. Instead, we\nstudy the zero-shot intent detection problem, which aims to detect emerging\nuser intents where no labeled utterances are currently available. We propose\ntwo capsule-based architectures: INTENT-CAPSNET that extracts semantic features\nfrom utterances and aggregates them to discriminate existing intents, and\nINTENTCAPSNET-ZSL which gives INTENTCAPSNET the zero-shot learning ability to\ndiscriminate emerging intents via knowledge transfer from existing intents.\nExperiments on two real-world datasets show that our model not only can better\ndiscriminate diversely expressed existing intents, but is also able to\ndiscriminate emerging intents when no labeled utterances are available.","url_abs":"http://arxiv.org/abs/1809.00385v1","url_pdf":"http://arxiv.org/pdf/1809.00385v1.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":"zero-shot-user-intent-detection-via-capsule","repo_url":"https://github.com/congyingxia/ZeroShotCapsule","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"zero-shot-user-intent-detection-via-capsule","repo_url":"https://github.com/diridiri/ZeroShotCapsule","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"zero-shot-user-intent-detection-via-capsule","repo_url":"https://github.com/joel-huang/zeroshot-capsnet-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"zero-shot-user-intent-detection-via-capsule","repo_url":"https://github.com/nhhoang96/ZeroShotCapsule-PyTorch-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"intent-detection","task_name":"Intent Detection"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.00385","atlas_url":"https://app.syntology.ai/?focus=1809.00385","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}