Document Re-ranking via Wikipedia Articles for Definition/Biography Type Questions

In this paper, we propose a document re-ranking approach based on the Wikipedia articles related to the specific questions to re-order the initial retrieved documents to improve the precision of top retrieved documents in Chinese information retrieval for question answering (IR4QA) system where the questions are definition or biography type. On one hand, we compute the similarity between each document in the initial retrieved results and the related Wikipedia article. On the other hand, we do clustering analysis for the documents based on the K-Means clustering method and compute the similarity between each centroid of the clusters and the Wikipedia article. Then we integrate the two kinds of similarity with the initial ranking score as the last similarity value and re-rank the documents in descending order with this measure. Experiment results demonstrate that this approach can improve the precision of the top relevant documents effectively.