Two robust semi-supervised learning algorithms for natural language processing

Add to your list(s) Download to your calendar using vCal

• Anders Søgaard, University of Copenhagen
• Friday 19 November 2010, 12:00-13:00
• FW11, Computer Laboratory.

If you have a question about this talk, please contact Thomas Lippincott.

Labeled data is often short in supply in natural language processing, but semi-supervised learning of structured variables is a difficult task. Positive results often rely on extensive parameter-tuning. In this talk, I present two new semi-supervised learning algorithms that have shown to be very robust across applications and datasets with no or fixed parameters.

This talk is part of the NLIP Seminar Series series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• Department of Computer Science and Technology talks and seminars
• FW11, Computer Laboratory
• Graduate-Seminars
• Guy Emerson's list
• Interested Talks
• Language Sciences for Graduate Students
• NLIP Seminar Series
• PMRFPS's
• Simon Baker's List
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.