Abstract
The fundamental role of hypernymy in NLP has motivated the development of many methods for the automatic identification of this relation, most of which rely on word distribution. We investigate an extensive number of such unsupervised measures, using several distributional semantic models that differ by context type and feature weighting. We analyze the performance of the different methods based on their linguistic motivation. Comparison to the state-of-the-art supervised methods shows that while supervised methods generally outperform the unsupervised ones, the former are sensitive to the distribution of training instances, hurting their reliability. Being based on general linguistic hypotheses and independent from training data, unsupervised measures are more robust, and therefore are still useful artillery for hypernymy detection.
Original language | English |
---|---|
Title of host publication | Long Papers |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 65-75 |
Number of pages | 11 |
ISBN (Electronic) | 9781510838604 |
DOIs | |
State | Published - 2017 |
Event | 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Valencia, Spain Duration: 3 Apr 2017 → 7 Apr 2017 |
Publication series
Name | 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference |
---|---|
Volume | 1 |
Conference
Conference | 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 |
---|---|
Country/Territory | Spain |
City | Valencia |
Period | 3/04/17 → 7/04/17 |
Bibliographical note
Publisher Copyright:© 2017 Association for Computational Linguistics.
Funding
The authors would like to thank Ido Dagan, Alessandro Lenci, and Yuji Matsumoto for their help and advice. Vered Shwartz is partially supported by an Intel ICRI-CI grant, the Israel Science Foundation grant 880/12, and the German Research Foundation through the German-Israeli Project Cooperation (DIP, grant DA 1600/1-1). Enrico Santus is partially supported by HK PhD Fellowship Scheme under PF12-13656.
Funders | Funder number |
---|---|
DIP | PF12-13656, DA 1600/1-1 |
German-Israeli Project Cooperation | |
Intel ICRI-CI | |
Deutsche Forschungsgemeinschaft | |
Israel Science Foundation | 880/12 |