A study of using an out-of-box commercial MT system for query translation in CLIR

Recent availability of commercial online machine translation (MT) systems makes it possible for layman Web users to utilize the MT capability for cross-language information retrieval (CLIR). To study the effectiveness of using MT for query translation, we conducted a set of experiments using Google Translate, an online MT system provided by Google, for translating queries in CLIR. The experiments show that MT is an excellent tool for the query translation task, and with the help of relevance feedback, it can achieve significant improvement over the monolingual baseline. The MT based query translation not only works for long queries, but is also effective for the short Web queries. Categories and Subject Descriptors H.3.3 [Information Storage and Retrieval]: Query formulation General Terms Experimentation, Languages, Performance Keywords Cross-Language Information Retrieval, Query Translation, Machine Translation, Query Expansion, Relevance Feedback

• Type: Conference
• Year: 2008
• Where: CIKM
• Authors: Dan Wu, Daqing He, Heng Ji, Ralph Grishman
• Keywords: CIKM 2008, Cross-language Information Retrieval, Information Management, Machine Translation, Query Translation