Cross-Language Text Search Algorithm Based on Context-Compatible Algorithms

In this era of knowledge explosion, the Internet is filled with a flood of information; however, complex and various. With the increasing close exchanges of technical at home and abroad, cross-lingual searching algorithm becomes particularly important. This article studied on the cross-lingual text searching algorithm based on context compatibility. In this article, context was integrated into searching, to some extent of which ensures the accurate interpretation of words of cross-lingual and is able to search for relevant text more accurately at the same time, which can avoid complex syntax analysis of various language, and find a multilingual common as well as feasible way in searching. In addition, IK and kuromoji was chosen as the Chinese and Japanese word segmentation device respectively with the use of massive subtitles to create a corpus and then searching in the context of word co-frequency analogue sentence relationship. Based on the context compatibility algorithm to study on the cross-lingual text searching, we designed the preliminary experiment and carried it out with some distinction effect.