Difference between revisions of "Class Meeting for 10-707 9/29/2010"
From Cohen Courses
Jump to navigationJump to search
| (2 intermediate revisions by the same user not shown) | |||
| Line 2: | Line 2: | ||
=== Meta-Learning: Searn === | === Meta-Learning: Searn === | ||
| − | |||
| Line 15: | Line 14: | ||
=== Optional Readings === | === Optional Readings === | ||
| − | * to | + | * [http://hal3.name/docs/daume05laso.pdf Learning as Search Optimization: Approximate Large Margin Methods for Structured Prediction] An alternative formal analysis of Searn. |
| + | * [http://hal3.name/docs/daume09unsearn.pdf Unsupervised Search-based Structured Prediction]. Applying Searn to unsupervised and/or semi-supervised problems. | ||
Latest revision as of 16:49, 28 September 2010
This is one of the class meetings on the schedule for the course Information Extraction 10-707 in Fall 2010.
Meta-Learning: Searn
Required Readings
- Search-Based Structured Prediction, Dame, Langford and Marcu. This is a journal-length paper, but it's not very dense. We will not be going through the theorems in any detail.
- Searn in Practice Unpublished manuscript, Daume et al.
Optional Readings
- Learning as Search Optimization: Approximate Large Margin Methods for Structured Prediction An alternative formal analysis of Searn.
- Unsupervised Search-based Structured Prediction. Applying Searn to unsupervised and/or semi-supervised problems.
