Identifying Word Translation in Non_Parallel Texts

Common algorithms for sentence and word-alignment allow the automat ic identification of word translations from paxalhl texts. This s tudy suggests tha t the identification of word translations should also be possible with non-paxMlel and even unrelated texts. The method proposed is based on the assumption tha t there is a correlation between the pat terns of word cooccurrences in texts of different languages. 1 I n t r o d u c t i o n In a number of recent studies it has been shown that word translations can be automatical ly derived from the statistical distribution of words in bilingual paxallel texts (e. g. Catizone, Russell & Warwick, 1989; Brown et al., 1990; Dagan, Church & Gale, 1993; Kay & Rbscheisen, 1993). Most of the proposed algorithms first conduct an alignment of sentences, i. e. those palxs of sentences axe located that are translations of each other. In a second step a word alignment is performed by analyzing the correspondences of words in each pair of sentences. The results achieved with these algorithms have been found useful for the compilation of dictionaries, for checking the consistency of terminological usage in translations, and for assisting the terminological work of translators and interpreters. However, despite serious efforts in the compilation of corpora (Church & Mercer, 1993; Armstrong & Thompson, 1995) the availability of a large enough paxallel corpus in a specific field and for a given pair of languages will always be the exception, not the rule. Since the acquisition of non-paxallel texts is usually much easier, it would be desirable to have a program that can determine the translations of words from comparable or even unrelated texts.