Semantic Method for Query Translation

Mohd Amin Mohd Yunus, Roziati Zainuddin, and Noorhidawati Abdullah
Faculty of Computer Science and Information Technology, University of Malaya, Malaysia

 
Abstract: Cross language information retrieval presents huge ambiguous results as polysemy problems. Therefore, the semantic approach comes to solve the polysemy problem which that the same word may have different meanings according to the context of sentences. This paper presents semantic technique on queries for retrieving more relevant results in cross language information retrieval (CLIR) that concentrates on the Arabic, Malay or English query(s) translation (a dictionary based method) to retrieve documents according to query(s) translation. Therefore, semantic ontology significantly improves and expands the single query itself with more synonym and related words. The query however is to retrieve relevant documents across language boundaries. Therefore, this study is conducted with the purposes to investigate English-Malay-Arabic query(s) translation approach and vice versa against keywords and querywords based on total retrieve and relevant. Keywords and querywords retrieval are evaluated in the experiments in terms of precision and recall. In order to produce more significant results, semantic technique is therefore applied to improve the performance of CLIR.

Keywords: Semantic ontology, semantic query, cross language information retrieval, dictionary-based.

 

Received September 2, 2010; accepted May 24, 2011

  

Full Text