Active learning for deep semantic parsing

Long Duong, Hadi Afshar, Dominique Estival, Glen Pink, Philip Cohen, Mark Johnson

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contribution

1 Citation (Scopus)

Abstract

Semantic parsing requires training data that is expensive and slow to collect. We apply active learning to both traditional and “overnight” data collection approaches. We show that it is possible to obtain good training hyperparameters from seed data which is only a small fraction of the full dataset. We show that uncertainty sampling based on least confidence score is competitive in traditional data collection but not applicable for overnight collection. We evaluate several active learning strategies for overnight data collection and show that different example selection strategies per domain perform best.

Original languageEnglish
Title of host publicationACL 2018 The 56th Annual Meeting of the Association for Computational Linguistics
Subtitle of host publicationProceedings of the Conference, Vol. 2 (Short Papers)
EditorsIryna Gurevych, Yusuke Miyao
PublisherAssociation for Computational Linguistics (ACL)
Pages43-48
Number of pages6
Volume2
ISBN (Electronic)9781948087346
Publication statusPublished - 1 Jan 2018
Externally publishedYes
Event56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 - Melbourne, Australia
Duration: 15 Jul 201820 Jul 2018

Conference

Conference56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
CountryAustralia
CityMelbourne
Period15/07/1820/07/18

    Fingerprint

Cite this

Duong, L., Afshar, H., Estival, D., Pink, G., Cohen, P., & Johnson, M. (2018). Active learning for deep semantic parsing. In I. Gurevych, & Y. Miyao (Eds.), ACL 2018 The 56th Annual Meeting of the Association for Computational Linguistics: Proceedings of the Conference, Vol. 2 (Short Papers) (Vol. 2, pp. 43-48). [P18-2008] Association for Computational Linguistics (ACL).