|Title||Trada: a Tree-Based Ranking Function Adaptation Approach|
|Publication Type||Conference Paper|
|Year of Publication||2008|
|Authors||Keke Chen, Rongqing Lu, C.K. Wong, Gordon Sun, Larry Heck, Belle Tseng|
|Conference Name||17th ACM Conference on Information and Knowledge Management|
|Conference Location||Napa Valley, California|
Machine Learned Ranking approaches have shown successes in web search engines. With the increasing demands on de- veloping effective ranking functions for different search do- mains, we have seen a big bottleneck, i.e., the problem of insufficient training data, which has significantly limited the fast development and deployment of machine learned rank- ing functions for different web search domains. In this paper, we propose a new approach called tree based ranking func- tion adaptation ( tree adaptation ) to address this problem. Tree adaptation assumes that ranking functions are trained with regression-tree based modeling methods, such as Gra- dient Boosting Trees. It takes such a ranking function from one domain and tunes its tree-based structure with a small amount of training data from the target domain. The unique features include (1) it can automatically identify the part of model that needs adjustment for the new domain, (2) it can appropriately weight training examples considering both lo- cal and global distributions. Experiments are performed to show that tree adaptation can provide better-quality rank- ing functions for a new domain, compared to other modeling methods.