A Query Classification System based on Snippet Similarity for a One-Click Search

Tatsuya Tojima, Takashi Yukawa
2013 International Journal of Computer Applications  
This paper proposes a query classification system for a one-click search system that uses feature vectors based on snippet similarity. The proposed system targets the NTCIR-10 1CLICK-2 query classification subtask and classifies queries in Japanese and English into eight predefined classes by using support vector machines (SVMs). In the NTCIR-9 and NTCIR-10 tasks, most participants used complex features or rules that depend strongly on language characteristics. The authors propose a new method
more » ... hat uses feature vectors created by using snippet similarities instead of the above mentioned features. In the proposed method, feature vectors have fewer dimensions, provide better generalization, lower language dependency, and reduced computer resources. This method achieved accuracies of 0.93 for a Japanese task and 0.91 for an English task. General Terms: Machine Learning, Web Search
doi:10.5120/14077-2146 fatcat:uxcjxvwpqvhatm77o4ilxl4ehy