2016/12/14 by Vered Shwartz, Enrico Santus, Shwartz, Vered +3 · 2 citations
Computer Science · #Artificial intelligence #Artillery #Authorship Attribution and Profiling #Computation and Language (cs.CL) #Computer science #Context (archaeology) #Data mining #FOS: Computer and information sciences #Feature (linguistics) #Geography #Identification (biology) #Linguistics #Machine learning #Natural Language Processing Techniques #Natural language processing #Power (physics) #Relation (database) #Reliability (semiconductor) #Topic Modeling #Weighting #Word (group theory) #cs.CL
paper · pdf · doi:10.48550/arxiv.1612.04460
published in arXiv (Cornell University) (Cornell University) · EACL 2017. 9 pages
openalex publication_date 2016/12/14 · arxiv created 2017/01/08 · arxiv updated 2017/01/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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.