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 language | English (US) |
---|---|
Title of host publication | ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers) |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 644-649 |
Number of pages | 6 |
ISBN (Electronic) | 9781948087346 |
DOIs | |
State | Published - 2018 |
Event | 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 - Melbourne, Australia Duration: Jul 15 2018 → Jul 20 2018 |
Publication series
Name | ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) |
---|---|
Volume | 2 |
Conference
Conference | 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 |
---|---|
Country/Territory | Australia |
City | Melbourne |
Period | 7/15/18 → 7/20/18 |
Funding
This work was supported in part by NSF Grant IIS-1351029. We thank the anonymous reviewers for helpful comments.
ASJC Scopus subject areas
- Software
- Computational Theory and Mathematics