Year: 2018
Type: conference-paper
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.
DOI: 10.18653/v1/p18-2057
Authors: Stephen Roller, Douwe Kiela, Maximilian Nickel
Institutions: Meta (Israel), Meta (United States)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2798736886