Abstract
Methods for unsupervised hypernym detection may broadly be categorized according to two paradigms: pattern-based and distributional methods. In this paper, we study the performance of both approaches on several hypernymy tasks and find that simple pattern-based methods consistently outperform distributional methods on common benchmark datasets. Our results show that pattern-based models provide important contextual constraints which are not yet captured in distributional methods.- Anthology ID:
- P18-2057
- 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:
- 358–363
- Language:
- URL:
- https://aclanthology.org/P18-2057
- DOI:
- 10.18653/v1/P18-2057
- Cite (ACL):
- Stephen Roller, Douwe Kiela, and Maximilian Nickel. 2018. Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 358–363, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora (Roller et al., ACL 2018)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/P18-2057.pdf
- Code
- facebookresearch/hypernymysuite + additional community code
- Data
- HyperLex