English

Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora

Computation and Language 2018-06-11 v1

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.

Keywords

Cite

@article{arxiv.1806.03191,
  title  = {Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora},
  author = {Stephen Roller and Douwe Kiela and Maximilian Nickel},
  journal= {arXiv preprint arXiv:1806.03191},
  year   = {2018}
}

Comments

Accepted as a short paper to ACL 2018

R2 v1 2026-06-23T02:23:44.889Z