作者: Fernando Diaz , Rosie Jones
关键词: Set (abstract data type) 、 Data mining 、 Ranking (information retrieval) 、 Component (UML) 、 Measure (data warehouse) 、 Information retrieval 、 Computer science 、 Relevance feedback 、 Query expansion 、 Key (cryptography) 、 Language model
摘要: A key missing component in information retrieval systems is self-diagnostic tests to establish whether the system can provide reasonable results for a given query on document collection. If we measure properties of retrieved set documents which allow us predict average precision, automate decision elicit relevance feedback, or modify other ways. We use meta-data attached form time stamps distribution response query, over domain, create temporal profile query. define some useful features this profile. find that using these features, together with content retrieved, improve prediction precision