论文信息 - English–Hindi Translation in 21 Days

English–Hindi Translation in 21 Days

We present experiments with aMosesbased English-to-Hindi translation system. We evaluate the impact of additional out-of-domain training data, both parallel and Hindi-only, and experiment with three methods for improving word order: standard Moses reordering model, rule-based preprocessing and language-independent suffix identification.

Daniel Zeman | Ondřej Bojar | Pavel Straňák

[1] Franz Josef Och,et al. Minimum Error Rate Training in Statistical Machine Translation , 2003, ACL.

[2] Daniel Zeman. Unsupervised Acquiring of Morphological Paradigms from Tokenized Text , 2007, CLEF.

[3] Fernando Pereira,et al. Non-Projective Dependency Parsing using Spanning Tree Algorithms , 2005, HLT.

[4] Philipp Koehn,et al. Statistical Significance Tests for Machine Translation Evaluation , 2004, EMNLP.

[5] Philipp Koehn,et al. Moses: Open Source Toolkit for Statistical Machine Translation , 2007, ACL.

[6] Natalia Klyueva,et al. UMC 0.1: Czech-Russian-English Multilingual Corpus , 2008 .