Discriminative Alignment Training without Annotated Data for Machine Translation

Patrik Lambert (1) , Rafael E. Banchs (1) , Josep-Maria Crego (1)

1 UPC - Universitat Politècnica de Catalunya = Université polytechnique de Catalogne [Barcelona]

In present Statistical Machine Translation (SMT) systems, alignment is trained in a previous stage as the translation model. Consequently, alignment model parameters are not tuned in function of the translation task, but only indirectly. In this paper, we propose a novel framework for discriminative training of alignment models with automated translation metrics as maximization criterion. In this approach, alignments are optimized for the translation task. In addition, no link labels at the word level are needed. This framework is evaluated in terms of automatic translation evaluation metrics, and an improvement of translation quality is observed.

Mots clés: discriminative training; word alignment; machine translation

Domaines: Traitement du texte et du document

Patrik Lambert, Rafael E. Banchs, Josep-Maria Crego. Discriminative Alignment Training without Annotated Data for Machine Translation. Conference of the North American Chapter of the Association for Computational Linguistics, Apr 2007, United States. pp.85-88. ⟨hal-00430864⟩