The use of context in multiword-term translation

Abstract

The quality of a specialized translation depends to a great extent on the treatment of multiword terms (MWTs). Since MWTs are not always adequately described or even included in most terminological resources, translators and terminologists must find other ways to deal with them. One method involves the analysis of parallel texts. Traditionally, parallel texts have been a valuable resource for terminology extraction and knowledge acquisition. They can be compiled as comparable corpora (i.e. collections of texts originally written in the source and target languages). Nevertheless, even though comparable corpora can facilitate translation, many translators are often unfamiliar with corpus query techniques. This paper describes a method that identifies Spanish equivalents of English MWTs in corpora, and also provides translators and terminologists with a set of manual corpus query techniques that help to effectively translate MWTs. The comparable corpus compiled was composed of original English and Spanish texts on wind energy generation. The method proposed is based on distributional semantics and was used to identify and compare contextual elements of the concepts in both languages. The results of our study showed that this procedure simplifies and contributes to the accurate identification of MWT translation equivalents in corpora.