Data Inferred Multi-word Expressions for Statistical Machine Translation

Patrik Lambert (1) , Rafael E. Banchs (1)

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

This paper presents a strategy for detecting and using multi-word expressions in Statistical Machine Translation. Performance of the proposed strategy is evaluated in terms of alignment quality as well as translation accuracy. Evaluations are performed by using the Verbmobil corpus. Results from translation tasks from English-to-Spanish and from Spanish-to-English are presented and discussed.

Domaines: Traitement du texte et du document; Informatique et langage [cs.CL]

Patrik Lambert, Rafael E. Banchs. Data Inferred Multi-word Expressions for Statistical Machine Translation. Proceedings of Machine Translation Summit X, Sep 2005, Phuket, Thailand. pp.396-403. ⟨hal-00705007⟩