On domain similarity and effectiveness of adapting-to-rank

Adapting to rank address the the problem of insufficient domainspecific labeled training data in learning to rank. However, the initial study shows that adaptation is not always effective. In this paper, we investigate the relationship between the domain similarity and the effectiveness of domain adaptation with the help of two domain similarity measure: relevance correlation and sample distribution correlation. Categories and Subject Descriptors H.3.3 [Information Search and Retrieval]: Retrieval Models General Terms Algorithms Keywords Learning to Rank, Model Adaptation, Similarity Measure

• Type: Conference
• Year: 2009
• Where: CIKM
• Authors: Keke Chen, Jing Bai, Srihari Reddy, Belle L. Tseng
• Keywords: CIKM 2009, Database, Domain Similarity, Domain Similarity Measure, Similarity Measure