The effect of a general lexicon in corpus-based identification of French-English medical word translations.

We present a method, based on the similarity of word distribution across languages, of finding 'new' words' translations in French-English comparable medical texts, starting from a partial bilingual medical lexicon. In this paper, we test the influence of adding general-language words to this initial lexicon. Our experimental results show that all test words are correctly translated within the top 25 candidates; and that the addition of general words to the lexicon helps to improve translation accuracy for medical words.