Hypernyms under Siege: Linguistically-motivated Artillery for Hypernymy Detection
This work addresses hypernymy detection for NLP applications, but it is incremental as it focuses on analyzing existing methods rather than introducing new ones.
The paper tackled hypernymy detection in NLP by evaluating unsupervised distributional methods against supervised ones, finding that supervised methods outperform but are less reliable due to training data sensitivity, while unsupervised methods are more robust.
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.