Finding similar questions with categorization information and dependency syntactic tree

  • Authors:

  • Xin Lian;Xiaojie Yuan;Xiangyu Hu;Haiwei Zhang

  • Affiliations:

  • Institute of Computer Science and Technology, Nankai University, Tianjin, China;Institute of Computer Science and Technology, Nankai University, Tianjin, China;Institute of Computer Science and Technology, Nankai University, Tianjin, China;Institute of Computer Science and Technology, Nankai University, Tianjin, China

  • Venue:
  • WAIM'13 Proceedings of the 14th international conference on Web-Age Information Management
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

Question Answering communities rapidly build up large archives of questions and answers. One of the major tasks in a question and answer service is to find similar questions to a new question. Question retrieval in the CQA sites is different from web search. It doesn't take advantage of the features of CQA sites to introduce natural language to solve the problem. In this paper, we address this problem by utilizing more features of CQA sites, including question, description, answer, category and users' posted questions. The model is divided into question classification and question retrieval. Question classification prunes the search space and removes some noise. Then "dependency syntactic tree" is made use of to find similar questions within the predetermined categories. The experimental results show that our approach leads to a better performance than other approaches.