Term-list Translation Using Mono-lingual Word Co-occurrence Vectors

A term-list is a list of content words that characterize a consistent text or a concept. This paper presents a new method for translating a term-list by using a corpus in the target language. The method rst retrieves alternative translations for each input word from a bilingual dictionary. It then determines the most`coherent' combination of alternative translations , where the coherence of a set of words is deened as the proximity among multi-dimensional vectors produced from the words on the basis of co-occurrence statistics. The method was applied to term-lists extracted from newspaper articles and achieved 81% translation accuracy for ambiguous words (i.e., words with multiple translations).