Abstract
In this paper, we proposed a Query Expansion (QE) approach on a Turkish Text collection based on word-context matrix with a sliding fixed sized window and Singular Value Decomposition (SVD) method. Our query expansion approach uses semantic relationship of terms to improve the existing query expansion methods available in the literature, namely Bo1 (Bose-Einstein 1), Bo2 (Bose-Einstein 2) and KL (Kullback-Leibler). We evaluated our approach on Milliyet collection, which is a Turkish IR test bed containing more than 400K documents and 72 queries. The experimentation shows that our approach clearly improves the all three QE methods in terms of major Information Retrieval (IR) performance measures such as MAP, R-precision and P@10.
Highlights
As a result of rapid development of Internet and related technologies, the amount of data is growing day by day
If a word is included in both results, we added this word to the query
First we performed our baseline evaluations without any query expansion
Summary
As a result of rapid development of Internet and related technologies, the amount of data is growing day by day. This data has to be organized and retrieved whenever it is needed. Information Retrieval (IR) is a discipline that is related with indexing, retrieving, and structuring documents from any collections. The retrieval methods aim to find the best matching documents according to user query (user need) within a large document collection. In general users may not know how to construct the best query according to their needs and the queries may be inadequate. Query Expansion (QE) is the process of reformulating the basic user query in order to get a better retrieving performance. Different techniques can be conducted to expand a query such as using synonyms of terms, using ontologies to add related terms, or checking spelling errors of terms and correcting them
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
