Local lexical adaptation in Machine Translation through triangulation: SMT helping SMT

We present a framework where auxiliary MT systems are used to provide lexical predictions to a main SMT system. In this work, predictions are obtained by means of pivoting via auxiliary languages, and introduced into the main SMT system in the form of a low order language model, which is estimated on a sentenceby-sentence basis. The linear combination of models implemented by the decoder is thus extended with this additional language model. Experiments are carried out over three different translation tasks using the European Parliament corpus. For each task, nine additional languages are used as auxiliary languages to obtain the triangulated predictions. Translation accuracy results show that improvements in translation quality are obtained, even for large data conditions.

• Type: Journal
• Year: 2010
• Where: COLING
• Authors: Josep Maria Crego, Aurélien Max, François Yvon
• Keywords: Auxiliary Languages, COLING 2010, Computational Linguistics, Language Model, Main Smt