Phrasal Segmentation Models for Statistical Machine Translation

Phrasal segmentation models define a mapping from the words of a sentence to sequences of translatable phrases. We discuss the estimation of these models from large quantities of monolingual training text and describe their realization as weighted finite state transducers for incorporation into phrase-based statistical machine translation systems. Results are reported on the NIST Arabic-English translation tasks showing significant complementary gains in BLEU score with large 5-gram and 6-gram language models.

• Type: Conference
• Year: 2008
• Where: COLING
• Authors: Graeme W. Blackwood, Adrià de Gispert, William Byrne
• Keywords: COLING 2008, Computational Linguistics, NIST Arabic-English Translation, Phrasal Segmentation Models, Phrase-based Statistical Machine