A Novel Method to Improve the Retrieved Multilingual Documents Score

With an ever-increasing number of resources on the Web, different language resources such as newspapers, magazines, and articles have become available. This demands for an improved technique in the information retrieval to extirpate the communication barrier among languages. Search engines are the cornerstones for informational contents and the link between the two parties of publishing and retrieval of content. Moreover, the search for information is no longer narrowed to users of the native language of the original source. Most of the non-English users such as Arabic speakers are unable to express the terms in their own language. Also, the terminologies written in the native language of the source are acquired from the English language. This challenge drives users to use mixed terms (multilingual terms) to get better results, especially in the scientific domain. This paper attempts to address the problem of documents retrieval using multilingual queries. When users use mixed queries, the results of the multilingual documents will dominate the top of the retrieved documents rather than other relevant documents, and the scores of the mixed documents obtain extra weight values that are not really part of their actual weighting value. This paper proposes a novel method to improve the results of the retrieved documents by adjusting the score of multilingual documents. For experiments, we used a mixed test collection containing mixedlanguage documents (Arabic and English). The results showed that the proposed method led to an enhanced performance in documents retrieval from multilingual queries which made them relevant, effective and accurate thus proving that our approach is more reliable than other traditional approaches.