TY - GEN
T1 - Language models for machine translation
T2 - Conference on Empirical Methods in Natural Language Processing, EMNLP 2011
AU - Lembersky, Gennadi
AU - Ordan, Noam
AU - Wintner, Shuly
N1 - Funding Information: The first author would like to thank Esther and Kiri for their loving support.
PY - 2011
Y1 - 2011
N2 - We investigate the differences between language models compiled from original target-language texts and those compiled from texts manually translated to the target language. Corroborating established observations of Translation Studies, we demonstrate that the latter are significantly better predictors of translated sentences than the former, and hence fit the reference set better. Furthermore, translated texts yield better language models for statistical machine translation than original texts.
AB - We investigate the differences between language models compiled from original target-language texts and those compiled from texts manually translated to the target language. Corroborating established observations of Translation Studies, we demonstrate that the latter are significantly better predictors of translated sentences than the former, and hence fit the reference set better. Furthermore, translated texts yield better language models for statistical machine translation than original texts.
UR - http://www.scopus.com/inward/record.url?scp=80053235090&partnerID=8YFLogxK
M3 - Conference contribution
SN - 1937284115
SN - 9781937284114
T3 - EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
SP - 363
EP - 374
BT - EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
Y2 - 27 July 2011 through 31 July 2011
ER -