en
0.25
0.5
0.75
1.25
1.5
1.75
2
Multiview Semi-Supervised Learning for Ranking Multilingual Documents
Published on Nov 30, 20112419 Views
We address the problem of learning to rank documents in a multilingual context, when reference ranking information is only partially available. We propose a multiview learning approach to this semisup
Chapter list
Multiview Semi-Supervised Learning for Ranking Multilingual Documents00:00
Ranking Multilingual Documents - 100:29
Ranking Multilingual Documents - 201:08
Semisupervised Ranking of Multilingual Documents02:09
Index - 103:45
Multiview ranking framework04:01
Ranking Risk(s)06:15
(Dis)Agreement Constraint09:01
Disagreement for Bipartite Ranking11:02
Index - 212:30
Algorithm12:32
Semisupervised Multiview Ranking Algorithm15:23
Index - 316:27
Experiments: Data16:29
Experiments: Models17:03
Experiments: Performance (AUC)18:01
Performance vs. training set size18:42
Disagreement during learning18:56
Effect of class imbalance19:23
Comparison with concatenated views19:25
Index - 420:00
Conclusion20:01
The end21:04