Potential Reading

Future Readings

Below is a list of papers, articles, etc that should serve as a pool for selecting readings for future CompSem meetings. If you see a paper you would like to read and discuss please post it here, so that we can queue it up.

Paper	Tags	Rationale	Added by
Probabilistic Topic Models, Steyvers	topic modeling, Latent Dirichlet Allocation (LDA)	Looks like it provides an easier introduction to topic models than the original Blei paper
"Finding Scientific Topics", Steyvers and Griffiths	topic modeling, Latent Dirichlet Allocation (LDA)	Potentially another good explanation of a generative topic model
Dependency Parsing by Belief Propagation Smith, David A. and Jason Eisner (2008)	Belief Propagation, Dependency Parsing	Jason Eisner gave a very interesting keynote talk at the workshop on Semi-Supervised Learning at NAACL 2009 which references this paper
Semi-supervised Learning Literature Survey Xiaojin Zhu (2008)	Semi-supervised learning	I'll be happy if we get through the first few pages	Dima
Learning with labeled and unlabeled data Matthias Seeger (2002)	Semi-supervised learning	An older survey	Dima
Text Classification from Labeled and Unlabeled Documents using EM Nigram et al. (2000)	Semi-supervised learning	An early semi-supervised learning paper; might be more readable than more recent papers	Dima
Frustratingly Easy Domain Adaptation Hal Daume III (2007)	Domain Adaptation	Some kind of magic	Dima
Transfer Learning for Text Classification Do and Ng (2005)	Transfer Learning	What in the world is transfer learning? I have no idea but I want to find out.	Dima
Using Linguistic Cues for the Automatic Recognition of Personality in Conversation and Text Francois Mairesse, Marilyn Walker, Matthias Mehl and Roger Moore (2007)	content analysis, discourse processing	sort of a different paper for the group	Will
Attention, Intentions, and the Structure of Discourse (1986) Barbara J. Grosz, Candace L. Sidner	discourse processing	a classic paper in discourse modeling for computational purposes	Will
Deep Learning for NLP (without Magic) Richard Socher and Chris Manning (2013)	Deep Learning Tutorial (Slides)	On deep learning in NLP	Arafat

For some ideas you might look at other reading groups:

* Johns Hopkins NLP Reading Group
* Stanford NLP Reading Group