Publication at Faculty of Mathematics and Physics |
2015
Abstract
In this paper we will explore different approaches used in cross languages information retrieval (CLIR) systems, mainly dictionary-based and corpus based systems. Then we will focus on CLIR systems which use statistical machine translation (SMT) systems to translate queries into collection language.
Different approaches which use SMT are studied in this paper including the using of SMT as black box and looking inside the box of the SMT system to tune it to get better performance in IR’s point of views rather than using SMT system to give better results for human’s point of views.