Paper: Language Models for Machine Translation: Original vs. Translated Texts

ACL ID D11-1034
Title Language Models for Machine Translation: Original vs. Translated Texts
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2011
Authors

We investigate the differences between language models compiled from original target-language texts and those compiled from texts manually translated to the tar- get language. Corroborating established observations of Translation Studies, we demonstrate that the latter are signifi- cantly better predictors of translated sen- tences than the former, and hence fit the reference set better. Furthermore, trans- lated texts yield better language mod- els for statistical machine translation than original texts.