Using word alignments to assist computer-aided translation users by marking which target-side words to change or keep unedited

Abstract

This paper explores a new method to improve computer-aided translation (CAT) systems based on translation memory (TM) by using pre-computed word alignments between the source and target segments in the translation units (TUs) of the user’s TM. When a new segment is to be translated by the CAT user, our approach uses the word alignments in the matching TUs to mark the words that should be changed or kept unedited to transform the proposed translation into an adequate translation. In this paper, we evaluate different sets of alignments obtained by using GIZA++. Experiments conducted in the translation of Spanish texts into English show that this approach is able to predict which target words have to be changed or kept unedited with an accuracy above 94% for fuzzy-match scores greater or equal to 60%. In an appendix we evaluate our approach when new TUs (not seen during the computation of the word-alignment models) are used.