Corpus-Based Extension of Semantic Lexicons in Large Scale

During recent years there has been an increased interest to acquire or extend, on a large-scale, highquality semantic lexicons. The methodology is usually corpus-driven. It is based on the (re-)use of machine readable resources of various types, and the application of cost effective ways to eliminate the acquistion bottleneck, i.e. derivational morphology, customization of off-the-shelf resources, statistical techniques and shallow parsing. This paper investigates how, and to what extent the flexibility and robustness of a partial parser can be utilized to fully automatically achieve this goal. Our work is based on the observation that members of a semantic group are often surrounded by other members of the same group in text. Given a few category members we use parsed corpora to collect surrounding contexts and try to identify other words that also belong to the same group.