Sciweavers

Share
ACL
2012

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

8 years 2 months ago
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.
Preslav Nakov, Jörg Tiedemann
Added 29 Sep 2012
Updated 29 Sep 2012
Type Journal
Year 2012
Where ACL
Authors Preslav Nakov, Jörg Tiedemann
Comments (0)
books