Title :
Translating OOV phrases based on lexical information and web mining
Author :
Sun, Guihua ; Xu, Gaopan ; Zhang, Ke
Author_Institution :
Dept. of Comput., Xiamen Univ. of Technol., Xiamen, China
Abstract :
This paper presents a novel approach to improve the OOV (Out-of-vocabulary) phrase translation by combining lexical information and web mining. We first retrieve the top relevant anchor words with source OOV phrase from search engine, and then search the translation with expanded query ¿source OOV phrase + anchor word¿ from mixed-language web pages. Finally, a ME (Maximum Entropy) model is employed to rank returned translation candidates by combining lexical similarity and statistical similarity. Experiment results show our approach is promising.
Keywords :
data mining; language translation; search engines; Web mining; lexical information; maximum entropy; mixed-language Web pages; out-of-vocabiilary phrase translation; search engine; Books; Data mining; Intelligent systems; Knowledge engineering; Motion pictures; Natural languages; Search engines; Sun; Web mining; Web pages;
Conference_Titel :
Intelligent System and Knowledge Engineering, 2008. ISKE 2008. 3rd International Conference on
Conference_Location :
Xiamen
Print_ISBN :
978-1-4244-2196-1
Electronic_ISBN :
978-1-4244-2197-8
DOI :
10.1109/ISKE.2008.4731037
