作者: Ben He , Iadh Ounis
DOI: 10.1007/978-3-540-30213-1_5
关键词:
摘要: The prediction of query performance is an interesting and important issue in Information Retrieval (IR). Current predictors involve the use relevance scores, which are time-consuming to compute. Therefore, current not very suitable for practical applications. In this paper, we study a set performance, can be generated prior retrieval process. linear non-parametric correlations with thoroughly assessed on TREC disk4 disk5 (minus CR) collections. According results, some proposed have significant correlation showing that these useful infer