Download | - View accepted manuscript: A Boosting Algorithm for Learning Bipartite Ranking Functions with Partially Labeled Data (PDF, 767 KiB)
|
---|
Author | Search for: Amini, Massih-Reza; Search for: Truong, Tuong-Vinh; Search for: Goutte, Cyril1 |
---|
Affiliation | - National Research Council of Canada. NRC Institute for Information Technology
|
---|
Format | Text, Article |
---|
Conference | 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2008), Singapore, July 20-24, 2008 |
---|
Subject | Learning to Rank with partially labeled data; Boosting; Information Routing |
---|
Abstract | a bipartite ranking function (BRF) with partially labeled data. Until now different attempts had been made to build a BRF in a transductive setting, in which the test points are given to the methods in advance as unlabeled data. The proposed approach is a semi-supervised inductive ranking algorithm which, as opposed to transductive algorithms, is able to infer an ordering on new examples that were not used for its training. We evaluate our approach using the TREC-9 Ohsumed and the Reuters-21578 data collections, comparing against two semi-supervised classification algorithms for ROCArea (AUC), uninterpolated average precision (AUP), mean precision@50 (mT9P) and Precision-Recall (PR) curves. In the most interesting cases where there are an unbalanced number of irrelevant examples over relevant ones, we show our method to produce statistically significant improvements with respect to these ranking measures. |
---|
Publication date | 2008 |
---|
In | |
---|
Language | English |
---|
Peer reviewed | Yes |
---|
NPARC number | 16335051 |
---|
Export citation | Export as RIS |
---|
Report a correction | Report a correction (opens in a new tab) |
---|
Record identifier | ebeea32c-9cc4-4574-86dd-a87d37188b09 |
---|
Record created | 2010-11-05 |
---|
Record modified | 2020-04-15 |
---|