When Hearst Is not Enough: Improving Hypernymy Detection from Corpus with Distributional Models

Changlong Yu, Jialong Han, Peifeng Wang, Yangqiu Song, Hongming Zhang, Wilfred Ng, Shuming Shi


Abstract
We address hypernymy detection, i.e., whether an is-a relationship exists between words (x ,y), with the help of large textual corpora. Most conventional approaches to this task have been categorized to be either pattern-based or distributional. Recent studies suggest that pattern-based ones are superior, if large-scale Hearst pairs are extracted and fed, with the sparsity of unseen (x ,y) pairs relieved. However, they become invalid in some specific sparsity cases, where x or y is not involved in any pattern. For the first time, this paper quantifies the non-negligible existence of those specific cases. We also demonstrate that distributional methods are ideal to make up for pattern-based ones in such cases. We devise a complementary framework, under which a pattern-based and a distributional model collaborate seamlessly in cases which they each prefer. On several benchmark datasets, our framework demonstrates improvements that are both competitive and explainable.
Anthology ID:
2020.emnlp-main.502
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6208–6217
Language:
URL:
https://aclanthology.org/2020.emnlp-main.502
DOI:
10.18653/v1/2020.emnlp-main.502
Bibkey:
Cite (ACL):
Changlong Yu, Jialong Han, Peifeng Wang, Yangqiu Song, Hongming Zhang, Wilfred Ng, and Shuming Shi. 2020. When Hearst Is not Enough: Improving Hypernymy Detection from Corpus with Distributional Models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6208–6217, Online. Association for Computational Linguistics.
Cite (Informal):
When Hearst Is not Enough: Improving Hypernymy Detection from Corpus with Distributional Models (Yu et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.502.pdf
Video:
 https://slideslive.com/38939044
Code
 HKUST-KnowComp/ComHyper