Quarterly (March, June, September, December)
160 pp. per issue
6 3/4 x 10
ISSN
0891-2017
E-ISSN
1530-9312
2014 Impact factor:
1.23

Computational Linguistics

Paola Merlo, Editor
December 2012, Vol. 38, No. 4, Pages 799-825
(doi: 10.1162/COLI_a_00111)
© 2012 Association for Computational Linguistics
Language Models for Machine Translation: Original vs. Translated Texts
Article PDF (199.53 KB)
Abstract

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.