Hypernyms under Siege: Linguistically-motivated Artillery for Hypernymy Detection

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.

PDF Abstract EACL 2017 PDF EACL 2017 Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Hypernym Discovery General balAPInc MAP 1.36 # 8
MRR 3.18 # 8
P@5 1.30 # 8
Hypernym Discovery Medical domain balAPInc MAP 0.91 # 8
MRR 2.10 # 8
P@5 1.08 # 8
Hypernym Discovery Music domain balAPInc MAP 1.95 # 7
MRR 5.01 # 7
P@5 2.15 # 7

Methods


No methods listed for this paper. Add relevant methods here