The purpose of this project is to investigate and propose a practical approach dealing with the increasingly important issue - cross-language information retrieval(CLIR), especially in the Internet environment. The traditional approaches of select-all, select-one, and select-top-n are investigated for performance in cross-language information retrieval. Two implicit problems in CLIR have also be made significant in this research: one the translation ambiguity; the other is target polysemy. New resolutions to the problems are proposed and a series of experiments are carried out. The results show that the proposed approaches are significant and promising.
|Appears in Collections:||圖書資訊學系|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.