Combining Evidence for Relevance Criteria: A Framework and Experiments in Web Retrieval

Abstract. We present a framework that assesses relevance with respect to several relevance criteria, by combining the query-dependent and query-independent evidence indicating these criteria. This combination of evidence is modelled in a uniform way, irrespective of whether the evidence is associated with a single document or related documents. The framework is formally expressed within Dempster-Shafer theory. It is evaluated for web retrieval in the context of TREC’s Topic Distillation task. Our results indicate that aggregating content-based evidence from the linked pages of a page is beneficial, and that the additional incorporation of their homepage evidence further improves the effectiveness. Key words: Dempster-Shafer theory, Topic Distillation task 1 Motivation, Background, and Aim In ad-hoc Information Retrieval (IR), multiple criteria are applied when assessing the relevance of documents. The relevance criterion at the heart of IR, and the one usually employed by IR system...

• Type: Conference
• Year: 2007
• Where: ECIR
• Authors: Theodora Tsikrika, Mounia Lalmas
• Keywords: ECIR 2007, Information Technology, Relevance Criteria, Topic Distillation Task, Topical Relevance