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.
|Title of host publication||EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference|
|Number of pages||12|
|State||Published - 2011|
|Event||Conference on Empirical Methods in Natural Language Processing, EMNLP 2011 - Edinburgh, United Kingdom|
Duration: 27 Jul 2011 → 31 Jul 2011
|Name||EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference|
|Conference||Conference on Empirical Methods in Natural Language Processing, EMNLP 2011|
|Period||27/07/11 → 31/07/11|
Bibliographical noteFunding Information:
The first author would like to thank Esther and Kiri for their loving support.
ASJC Scopus subject areas
- Computational Theory and Mathematics
- Computer Science Applications
- Information Systems