event thumbnail image
Neural Information Processing Systems - NIPS05 Workshops

Learning Rankings for Information Retrieval

author: Thorsten Joachims, Cornell University
You might be experiencing some problems with Your Video player.
Slides
0:00 Learning Rankings for Information Retrieval
0:35 Ranked Information Retrieval
1:49 Learning Ranking Functions in IR
3:45 Rankings as Structured Outputs
4:58 Why Predict a Ranking?
6:01 Why Predict a Ranking?1
7:49 Why Predict a Ranking?2
9:23 Why Predict a Ranking?3
10:44 Training to Optimize Ranking Performance
11:11 Overview of Argument
12:26 Related Work
15:03 Non-Linear Classification Loss
17:33 Multivariate Classification
18:24 Support Vector Machine
18:53 Multivariate Classification SVM
21:25 Multivariate SVM Optimization Problem
24:52 Multivariate SVM Generalizes Classification SVM
25:28 Sparse Approximation Algorithm
27:34 Polynomial Convergence Bound
28:07 ARGMAX
29:16 Multivariate Ranking SVM
31:10 Multivariate Ranking SVM for ROC Area
32:58 ARGMAX for ROC-Area
34:09 Multivariate ROC SVM
35:05 Multivariate Ranking SVM for AvgPrec
35:47 ARGMAX for Average Precision
37:04 Experiment: Generalization Performance
38:52 Experiment: Number of Iterations
39:17 Implementation in SVMstruct
39:49 Conclusions

Lecture rating

People found this lecture:
Worth seeing
because it is:
 Valuable and informative
Well presented
Easily understandable
Acceptably recorded
You need to login to cast your vote.

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Reviews and comments:

Comment1 Yin, September 22, 2007 at 2:36 p.m.:

The slides link does not work.


Comment2 Jing, October 12, 2007 at 10:14 p.m.:

As a Linux user I cannot view the majority of lectures on your site since they're only visible using WMP. Does one have to be a Microsoft client to benefit from videolectures?


Write your own review or comment: