Title

On Domain Similarity and Effectiveness of Adapting-to-Rank

Document Type

Conference Proceeding

Publication Date

11-2009

Find in a Library

Catalog Record

Abstract

Adapting to rank address the problem of insufficient domain-specific labeled training data in learning to rank. However, the initial study show 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 measures: relevance correlation and sample distribution correlation.

Comments

Presented at the 18th ACM Conference on Information and Knowledge Management, Hong Kong, China, November 2-6, 2009.

Catalog Record

Share

COinS