{"type":"ScholarlyArticle","title":"Open Intent Extraction from Natural Language Interactions (Extended Abstract)","authors":[{"name":"Nikhita Vedula","slug":"nikhita-vedula","given":"Nikhita","family":"Vedula","affiliation":""},{"name":"Nedim Lipka","slug":"nedim-lipka","given":"Nedim","family":"Lipka","affiliation":""},{"name":"Pranav Maneriker","slug":"pranav-maneriker","given":"Pranav","family":"Maneriker","affiliation":""},{"name":"Srinivasan Parthasarathy","slug":"srinivasan-parthasarathy","given":"Srinivasan","family":"Parthasarathy","affiliation":""}],"abstract":"Accurately discovering user intents from their written or spoken language plays a critical role in natural language understanding and automated dialog response. Most existing research models this as a classification task with a single intent label per utterance. Going beyond this formulation, we define and investigate a new problem of open intent discovery. It involves discovering one or more generic intent types from text utterances, that may not have been encountered during training. We propose a novel, domain-agnostic approach, OPINE, which formulates the problem as a sequence tagging task in an open-world setting. It employs a CRF on top of a bidirectional LSTM to extract intents in a consistent format, subject to constraints among intent tag labels. We apply multi-headed self-attention and adversarial training to effectively learn dependencies between distant words, and robustly adapt our model across varying domains. We also curate and release an intent-annotated dataset of 25K real-life utterances spanning diverse domains. Extensive experiments show that OPINE outperforms state-of-art baselines by 5-15% F1 score.","doi":"10.24963/ijcai.2021/663","url":"https://ijcai.org/proceedings/2021/663","pdf":"https://ijcai.org/proceedings/2021/0663.pdf","markdown":"https://ijcai.org/proceedings/2021/663.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/663","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":"Sister Conferences Best Papers","track":"Sister Conferences Best Papers","number":663,"pages":{"first":4844,"last":4848},"keywords":["Natural Language Processing: Natural Language Semantics","Natural Language Processing: NLP Applications and Tools","Natural Language Processing: Natural Language Processing","Machine Learning: Deep Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}