{"type":"ScholarlyArticle","title":"Learning Class-Transductive Intent Representations for Zero-shot Intent Detection","authors":[{"name":"Qingyi Si","slug":"qingyi-si","given":"Qingyi","family":"Si","affiliation":""},{"name":"Yuanxin Liu","slug":"yuanxin-liu","given":"Yuanxin","family":"Liu","affiliation":""},{"name":"Peng Fu","slug":"peng-fu","given":"Peng","family":"Fu","affiliation":""},{"name":"Zheng Lin","slug":"zheng-lin","given":"Zheng","family":"Lin","affiliation":""},{"name":"Jiangnan Li","slug":"jiangnan-li","given":"Jiangnan","family":"Li","affiliation":""},{"name":"Weiping Wang","slug":"weiping-wang","given":"Weiping","family":"Wang","affiliation":""}],"abstract":"Zero-shot intent detection (ZSID) aims to deal with the continuously emerging intents without annotated training data. However, existing ZSID systems suffer from two limitations: 1) They are not good at modeling the relationship between seen and unseen intents. 2) They cannot effectively recognize unseen intents under the generalized intent detection (GZSID) setting. A critical problem behind these limitations is that the representations of unseen intents cannot be learned in the training stage. To address this problem, we propose a novel framework that utilizes unseen class labels to learn Class-Transductive Intent Representations (CTIR). Specifically, we allow the model to predict unseen intents during training, with the corresponding label names serving as input utterances. On this basis, we introduce a multi-task learning objective, which encourages the model to learn the distinctions among intents, and a similarity scorer, which estimates the connections among intents more accurately. CTIR is easy to implement and can be integrated with existing ZSID and GZSID methods. Experiments on two real-world datasets show that CTIR brings considerable improvement to the baseline systems.","doi":"10.24963/ijcai.2021/540","url":"https://ijcai.org/proceedings/2021/540","pdf":"https://ijcai.org/proceedings/2021/0540.pdf","markdown":"https://ijcai.org/proceedings/2021/540.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/540","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Natural Language Processing","track":"Main Track","number":540,"pages":{"first":3922,"last":3928},"keywords":["Natural Language Processing: Natural Language Processing","Natural Language Processing: Text Classification"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}