Combining Word-Level and Character-Level Models for Machine Translation Between Closely-Related Languages

We propose several techniques for improving statistical machine translation between closely-related languages with scarce resources. We use character-level translation trained on n-gram-character-aligned bitexts and tuned using word-level BLEU, which we further augment with character-based transliteration at the word level and combine with a word-level translation model. The evaluation on Macedonian-Bulgarian movie subtitles shows an improvement of 2.84 BLEU points over a phrase-based word-level baseline.

• Type: Journal
• Year: 2012
• Where: ACL
• Authors: Preslav Nakov, Jörg Tiedemann
• Keywords: ACL 2012, Computational Linguistics, Statistical Machine Translation, Translation Model, Word Level