This paper proposes an unsupervised approach to automatically interpret noun compounds using semantic similarity. Our proposed unsupervised method is based on obtaining a large amount of robust evidence for NC interpretation. In order to obtain evidence sentences for semantic relations (SRs), we first acquired sentences containing both a head noun and its modifier in the form of SR defi-nitions. Then we determined the semantic relations represented in the sentences by looking at the nouns in the test instances (noun mapping) and verbs in the SR definitions (verb mapping). In the noun mapping, we measured the similarity between nouns in test instances and nouns in the collected sentences. In the verb mapping, we mapped the verbs of sentences onto those in the SR definitions. Finally, we built a statistical classifier to interpret noun compounds and evaluated it over 17 SRs defined in [1].
展开▼
