... belonging to a category, constructcontext vectors of classified terms, and associatecategories to previously unclassified terms de-pending on the similarity of their context (Tanevand Magnini, 2006). ... Section 3.2) it is not possible to constructa context vector or determine the replacement fit.Unsupervised methods use clustering of word-context vectors (Lin, 1998), co-occurrence (Yangand ... them (Royand Subramaniam, 2006), even if those relation-ships do not explicitly appear in the text. Thoughthese methods tackle inconsistency by addressingtaxonomy deduction globally, the relationships...