The Systran NLP Browser: An Application of Machine Translation Technology in Cross-Language Information Retrieval

Abstract

The approach of using an existing machine translation system in cross-language information retrieval, as usually proposed, consists of automatically translating queries, or even the entire textual database, from one language to another. The information that machine translation technology can provide to cross-language information retrieval has been more extensively explored at SYSTRAN. This chapter is a description of the implementation of SYSTRAN NLP Browser, a cross-linguistic multilingual information retrieval system based on SYSTRAN parsing and machine translation technology. The first section discusses the utilization of machine translation technology in cross-language information retrieval in general. The second section describes the implementation of the NLP Browser. The third section discusses the present approach and the current development status, followed by the conclusion.