Abstract

This paper describes a bootstrapping method for automatically tagging noun compounds with their corresponding semantic relations. Our work takes advantage of the collocation of senses of the noun compound constituents and also word similarity. We exploit this to generate a set of noun compounds from a set of previously tagged noun compounds by replacing one constituent of each noun compound with similar words that are derived from synonyms, hypernyms and sister words. We started with 200 “seed ” noun compounds and generated sets of derived noun compounds with accuracy ranging between 64.72 % and 70.78%. We also evaluated the utility of the automatically derived noun compounds when used in combination with existing noun compound interpretation methods. 1

Citations