• Title/Summary/Keyword: Heterogenous indexing term

Search Result 1, Processing Time 0.015 seconds

An Equation Retrieval System Based on Weighted Sum of Heterogenous Indexing Terms (이질적 색인어의 가중치 합에 기반한 수식 검색 시스템)

  • Shin, Jun-Soo;Kim, Hark-Soo
    • Journal of KIISE:Software and Applications
    • /
    • v.37 no.10
    • /
    • pp.745-750
    • /
    • 2010
  • To effectively retrieve mathematical documents including various equations, mathaware search engines are needed. In this paper, we propose a equation retrieval system which helps users effectively search structurally similar equations. The proposed system disassembles MathML equations into three types of heterogeneous indexing terms; operators, variables, and partial structures of equations. Then, it independently indexes the disassembled terms. When a user inputs a MathML equation, the proposed system searches and ranks equations using weighted sums of three language models for the heterogeneous indexing terms. In the experiments with 244,744 MathML equations, three proposed system showed reliable performances (a P@1 of 53% in the closed test and a P@1 of 63% in the open test).