WordNet Based Hybrid Model for Query Expansion
Abhishek Kumar Shukla, Sujoy Das, Pushpendra Kumar · 2021
An important task of the retrieval system is to maximize precision and recall value. Several methods have been introduced to achieve this goal. Query expansion is one of the methods that try to maximize the mean average precision value. The proposed method expands the original query by appending the mixture of terms retrieved from the local method (top "k" ranked initially retrieved documents) and global method respectively. FIRE 2011 adhoc English test collection has been used to evaluate the performance of the proposed method. The mean average precision of the proposed method is 0.3037. An improvement of 1.71% and 2.25% is observed with respect to the original query and BM25 model respectively.