Title :
Using Accessor Variety Features of Source Graphemes in Machine Transliteration of English to Chinese
Author :
Jiang, Mike Tian-Jian ; Kuo, Chan-Hung ; Hsu, Wen-Lian
Author_Institution :
Dept. of Comput. Sci., Nat. Tsing Hua Univ., Hsinchu, Taiwan
Abstract :
This work describes a grapheme-based approach of English-to-Chinese (E2C) transliteration, which includes many-to-many alignment models and conditional random fields using accessor variety (AV) as an additional feature based on source graphemes. Experimental results indicate that the AV of a given English segment can generally improve effectiveness of E2C transliteration.
Keywords :
language translation; English segment; English-to-Chinese transliteration; accessor variety features; conditional random fields; machine transliteration; many-to-many alignment models; source graphemes; Accuracy; Context; Entropy; Labeling; Prediction algorithms; Training; Training data; accessor variety; conditional random fields; direct orthographical mapping; expectation maximization; machine transliteration; named entity;
Conference_Titel :
Technologies and Applications of Artificial Intelligence (TAAI), 2011 International Conference on
Conference_Location :
Chung-Li
Print_ISBN :
978-1-4577-2174-8
DOI :
10.1109/TAAI.2011.30
