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.- Anthology ID:
- P18-2102
- Volume:
- Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Editors:
- Iryna Gurevych, Yusuke Miyao
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 644–649
- Language:
- URL:
- https://aclanthology.org/P18-2102
- DOI:
- 10.18653/v1/P18-2102
- Cite (ACL):
- Yiben Yang, Larry Birnbaum, Ji-Ping Wang, and Doug Downey. 2018. Extracting Commonsense Properties from Embeddings with Limited Human Guidance. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 644–649, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Extracting Commonsense Properties from Embeddings with Limited Human Guidance (Yang et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/P18-2102.pdf
- Code
- yangyiben/PCE