作者: M. Lalmas , Ian Ruthven , C.J. van Rijsbergen , R.M. Byrne , H. Sorensen
DOI:
关键词:
摘要: Relevance feedback techniques are designed to automatically improve a system's representation of query by using documents the user has marked as relevant. However, traditional relevance models suffer from number limitations that restrict their potential in supporting information seeking. One major is it does not incorporate behavioural aspects seeking - how and why users assess relevance. We propose should be viewed process explanation demonstrate this limitation can overcome theory based on abductive inference.