Sciweavers

Share
NAACL
2007

A Log-Linear Block Transliteration Model based on Bi-Stream HMMs

10 years 4 months ago
A Log-Linear Block Transliteration Model based on Bi-Stream HMMs
We propose a novel HMM-based framework to accurately transliterate unseen named entities. The framework leverages features in letteralignment and letter n-gram pairs learned from available bilingual dictionaries. Letter-classes, such as vowels/non-vowels, are integrated to further improve transliteration accuracy. The proposed transliteration system is applied to out-of-vocabulary named-entities in statistical machine translation (SMT), and a significant improvement over traditional transliteration approach is obtained. Furthermore, by incorporating an automatic spell-checker based on statistics collected from web search engines, transliteration accuracy is further improved. The proposed system is implemented within our SMT system and applied to a real translation scenario from Arabic to English.
Bing Zhao, Nguyen Bach, Ian R. Lane, Stephan Vogel
Added 30 Oct 2010
Updated 30 Oct 2010
Type Conference
Year 2007
Where NAACL
Authors Bing Zhao, Nguyen Bach, Ian R. Lane, Stephan Vogel
Comments (0)
books