An Empirical Investigation into Grammatically Constrained Contexts in Predicting Distributional Similarity
Dongqiang Yang, David M W Powers · 2007
The utility of syntactic dependencies in computing distributional similarity has not yet been fully investigated. Most research based on syntactically conditioned co-occurrences simply ignores the salience of grammatical relations and effectively merges syntactic dependencies into one ‘context’. Through calculating distributional similarity, we design two experiments to explore and evaluate the four major types of contexts that are conditioned on grammatical relations. The consistent results show that the headmodifier dependency plays an important role in predicting the semantic features of nouns and verbs, in contrast to other dependencies. 1