Computational semantics of noun compounds in a semantic space model

This study examines the ability of a semantic space model to represent the meaning of noun compounds such as “information gathering ” or “weather fore-cast”. A new algorithm, comparison, is proposed for computing compound vectors from constituent word vectors, and compared with other algorithms (i.e., predication and centroid) in terms of accu-racy of multiple-choice synonym test and similar-ity judgment test. The result of both tests is that the comparison algorithm is, on the whole, superior to other algorithms, and in particular achieves the best performancewhen noun compounds have emergent meanings. Furthermore, the comparison algorithm also works for novel noun compounds that do not occur in the corpus. These findings indicate that a semantic space model in general and the compari-son algorithm in particular has sufficient ability to compute the meaning of noun compounds.