Phrase table pruning for Statistical Machine Translation

Esther Galbrun (1)

1 Helsingin yliopisto = Helsingfors universitet = University of Helsinki

Phrase-Based Statistical Machine Translation systems model the translation process using pairs of corresponding sequences of words extracted from parallel corpora. These biphrases are stored in phrase tables that typically contain several millions such entries, making it difficult to assess their quality without going to the end of the translation process. Our work is based on the examplifying study of phrase tables generated from the Europarl data, from French to English. We give some statistical information about the biphrases contained in the phrase table, evaluate the coverage of previously unseen sentences and analyse the effects of pruning on the translation.

Mots clés: Phrase-Based Statistical Machine Translation; Phrase table

Domaines: Intelligence artificielle [cs.AI]

Esther Galbrun. Phrase table pruning for Statistical Machine Translation. [Technical Report] C-2009-22, University of Helsinki. 2009, pp.38. ⟨hal-01399371⟩