The Effectiveness of Simple Hybrid Systems for Hypernym Discovery
William Held, Nizar Y. Habash · 2019
Hypernymy modeling has largely been separated according to two paradigms, patternbased methods and distributional methods.However, recent works utilizing a mix of these strategies have yielded state-of-the-art results.This paper evaluates the contribution of both paradigms to hybrid success by evaluating the benefits of hybrid treatment of baseline models from each paradigm.Even with a simple methodology for each individual system, utilizing a hybrid approach establishes new stateof-the-art results on two domain-specific English hypernym discovery tasks and outperforms all non-hybrid approaches in a general English hypernym discovery task.