Exploring N-grams Distribution for Sampling-based Alignment

Juan Luo (1) , Adrien Lardilleux (2) , Yves Lepage (1)

1 IPS - Graduate School of Information, Production and Systems
2 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur

We describe an approach to improve the performance of sampling-based multilingual alignment on translation tasks by investigating the distribution of n-grams in the translation tables. This approach consists in enforcing the alignment of n-grams. We compare the quality of phrase translation tables output by this approach and that of MGIZA++ in statistical machine translation tasks. We report significant improvements for this approach and show that merging translation tables outperforms state-of-the-art techniques.

Mots clés: phrase translation table; alignment; statistical machine translation task

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

Juan Luo, Adrien Lardilleux, Yves Lepage. Exploring N-grams Distribution for Sampling-based Alignment. 5th Language & Technology Conference (LTC'11), Nov 2011, Poznań, Poland. pp.5. ⟨hal-00650843⟩