[ Skip to the content ]

Institute of Formal and Applied Linguistics Wiki


[ Back to the navigation ]

This is an old revision of the document!


Reading Group

Official name of this course is NPFL095 Modern Methods in Computational Linguistics. It is a continuation of informal Reading Group (RG) meetings. Requirements for getting credits:

All questions, reports and presented papers must be in English. The presentations are in English by default, but if all present people agree it may be in Czech.

Contact popel@ufal.mff.cuni.cz
Mailing list rg@ufal.mff.cuni.cz
List Archive http://ufal.mff.cuni.cz/mailman/listinfo/rg
Meetings Mondays 16:00, room S1
Past meetings courses:rg:past
Inspiration courses:rg:wishlist

Spring&Summer 2013

date speaker paper
Feb 18 startup meeting
Feb 25 Martin Popel Mark Johnson: A brief introduction to kernel classifiers, 2009. You can also read a chapter from cimpl.info
Mar 4 Ondřej Dušek Michael Collins, Nigel Duffy: Convolution kernels for natural language, NIPS 2001.
Mar 11 Aron Culotta, Jeffrey Sorensen: Dependency Tree Kernels for Relation Extraction, ACL 2004.
Mar 18 Intro to Structured prediction. Michael Collins: Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms, EMNLP 2002. As for the intro, Ivan Titov or Hal Daumé have nice materials (Hal has many more).
Mar 25 Sara van de Moosdijk Andrew McCallum, Dayne Freitag, Fernando Pereira: Maximum Entropy Markov Models for Information Extraction and Segmentation, Conference on Machine Learning 2000, slides
Apr 1 no RG, Easter (and April Fool's Day)
Apr 8 John Lafferty, Andrew McCallum, Fernando Pereira: Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data, 2001
Apr 15 Ondřej Fiala Ashish Venugopal, Jakob Uszkoreit, David Talbot, Franz J. Och, Juri Ganitkevitch: Watermarking the Outputs of Structured Prediction with an application in Statistical Machine Translation, 2011
Apr 22
Apr 1
May 6
May 13
May 20 last RG

[ Back to the navigation ] [ Back to the content ]