Extracting commonsense properties from embeddings with limited human guidance

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

3 Scopus citations

Abstract

Intelligent systems require common sense, but automatically extracting this knowledge from text can be difficult. We propose and assess methods for extracting one type of commonsense knowledge, object-property comparisons, from pre-trained embeddings. In experiments, we show that our approach exceeds the accuracy of previous work but requires substantially less hand-annotated knowledge. Further, we show that an active learning approach that synthesizes common-sense queries can boost accuracy.

Original languageEnglish (US)
Title of host publicationACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)
PublisherAssociation for Computational Linguistics (ACL)
Pages644-649
Number of pages6
ISBN (Electronic)9781948087346
StatePublished - Jan 1 2018
Event56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 - Melbourne, Australia
Duration: Jul 15 2018Jul 20 2018

Publication series

NameACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Volume2

Conference

Conference56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
CountryAustralia
CityMelbourne
Period7/15/187/20/18

    Fingerprint

ASJC Scopus subject areas

  • Software
  • Computational Theory and Mathematics

Cite this

Yang, Y., Birnbaum, L. A., Wang, J., & Downey, D. C. (2018). Extracting commonsense properties from embeddings with limited human guidance. In ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers) (pp. 644-649). (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); Vol. 2). Association for Computational Linguistics (ACL).