Document-Level Machine Translation as a Re-translation Process

Resumen

Most of the current Machine Translation systems are designed to translate
a document sentence by sentence ignoring discourse information and producing
incoherencies in the nal translations. In this paper we present some documentlevel-oriented post-processes to improve translations' coherence and consistency. Incoherences are detected and new partial translations are proposed. The work focuses on studying two phenomena: words with inconsistent translations throughout a text and also, gender and number agreement among words. Since we deal with specific phenomena, an automatic evaluation does not reflect signicant variations in the translations. However, improvements are observed through a manual evaluation.