Corpora: Text Learning: Beyond Supervision (IJCAI workshop CFP)

[Lillian Lee]

======================================================================
			   CALL FOR PAPERS
			 IJCAI-01 Workshop on

		 "Text Learning: Beyond Supervision"

			Monday, 6 August 2001
		       Seattle, Washington, USA
		 www.cs.cmu.edu/~mccallum/textbeyond

		 Submission deadline: March 23, 2001


Due to the rapidly increasing amount of textual data available and the
range of interesting and important problems arising in text analysis,
there has been growing interest in applying machine learning
methods to text.  There has also been significant recent interest in
research that combines supervised and unsupervised learning.  This
research is especially relevant to text learning because the inherent
complexity of natural language usually requires models with many
parameters:  estimating those parameters requires a lot of data, and
obtaining labeled data is difficult and expensive.  By combining
unsupervised learning with supervised learning, the need for labeled
training data can often be greatly reduced, allowing for the
development of more powerful models and methods.

The workshop will explore machine learning methods for solving
supervised text learning tasks that exploit training methods beyond
straightforward supervised learning.

Relevant topics include:

* Text classification with labeled and unlabeled data: EM,
  co-training, transduction with SVMs, discriminative maximum entropy
  with unlabeled data.
* Information extraction with unlabeled data: bootstrapping,
  co-boosting.
* Part-of-speech tagging, parsing and other NLP with unlabeled data.
* Active learning: uncertainty sampling, query-by-committee, version
  space reduction.
* Model selection with unlabeled data.
* Word clustering for language modeling, distributional clustering,
  feature generation by clustering.
* Semi-supervised clustering, document clustering with user-feedback.
* Integrating prior knowledge into supervised learning, integrating
  distantly labeled data.
* Unsupervised methods for learning segmentation models, translation
  models, lexicons, etc.
* Link analysis for supervised learning.

The goal of this workshop is to bring together researchers from the
machine learning, information retrieval, computational linguistics and
language modeling to talk about their different perspectives and to
share their latest ideas.


INVITED SPEAKERS
----------------

David Yarowsky
Assistant Professor
Department of Computer Science
Johns Hopkins University
http://www.cs.jhu.edu/~yarowsky/

Tommi Jaakkola
Assistant Professor
Department of Computer Science
Massachusetts Institute of Technology
http://www.ai.mit.edu/people/tommi/tommi.html



SCHEDULE AND SUBMISSION PROCEDURE
---------------------------------

Friday, Mar 23 2001      Paper submissions due
Friday, Apr 06 2001      Acceptance notification
Friday, Apr 20 2001      Camera ready papers due

Authors are asked to prepare a paper in Postscript or PDF
format. Submissions should conform to the IJCAI-2001 format, and be 8
pages or less.  We encourage submissions containing original
theoretical and applied concepts.  Experimental results are also
encouraged, even if they are only preliminary. To submit a paper,
email it to textbeyond at whizbang.com before 6pm on the day of the
deadline.


ORGANIZING COMMITTEE
--------------------

Andrew McCallum
  WhizBang Labs - Research, 4616 Henry Street, Pittsburgh, PA  15218
  T: 412-683-9132 F: 412-683-4436
  mccallum at whizbang.com
  http://www.cs.cmu.edu/~mccallum

Kamal Nigam
  School of Computer Science, Carnegie Mellon, Pittsburgh, PA 15213
  T: 412-268-3070 F: 412-268-5576
  knigam at cs.cmu.edu
  http://www.cs.cmu.edu/~knigam

Tony Jebara
  MIT, Media Laboratory - 20 Ames Street, E15-390, Cambridge, MA 02138
  T: 617-253-0326 F: 617-253-8874
  jebara at media.mit.edu
  http://www.media.mit.edu/~jebara

Lillian Lee
  Department of Computer Science, Cornell University, Ithaca, NY 14853
  T: 607-255-8119 F: 607-255-4428
  llee at cs.cornell.edu
  http://www.cs.cornell.edu/home/llee