Detecting Hidden Multiwords in Bilingual Dictionaries

Dictionaries are a valuable source of information about multiwords. Unfortunately, only few multiwords are explicitly marked as such in dictionaries: most of them are presented without being distinguished from free combinations of words. In this paper we present a methodology for detecting hidden multiwords in bilingual dictionaries, along with their translation in another language. The methodology is based on a number of automatic procedures which exploit regularities in the different kinds of expressions that can be found in the Collins English-Italian bilingual dictionary to select those phrases that are most likely to contain multiwords. The quantitative results of the experiment are provided.