***** PLEASE DISTRIBUTE *****
Tackling the challenges of terascale human language problems
http://www-rohan.sdsu.edu/~malouf/terascale04.html
Workshop at ACL-2004
Barcelona, Spain, July 26, 2004
Description:
Machine learning methods form the core of most modern speech and
language processing technologies. Techniques such as kernel methods,
log-linear models, and graphical models are routinely used to classify
examples (e.g., to identify the topic of a story), rank candidates (to
order a set of parses for some sentence) or assign labels to sequences
(to identify named entities in a sentence). While considerable success
has been achieved using these algorithms, what has become increasingly
clear is that the size and complexity of the problems---in terms of
number of training examples, the size of the feature space, and the
size of the prediction space---are growing at a much faster rate than
our computational resources are, Moore's Law notwithstanding. This
raises real questions as to whether our current crop of algorithms
will scale gracefully when processing such problems. For example,
training Support Vector Machines for relatively small-scale problems,
such as classifying phones in the speech TIMIT dataset, will take an
estimated six years of CPU time (Salomon, et al. 2002). If we wished
to move to a larger domain and harness, say, all the speech data
emerging from a typical call center, then very clearly enormous
computational resources would be needed to be devoted to the task.
Allocation of such vast amounts of computational resources is beyond
the scope of most current research collaborations, which consist of
small groups of people working on isolated tasks using small networks
of commodity machines. The ability to deal with large-scale speech and
language problems requires a move away from isolated individual groups
of researchers towards co-ordinated `virtual organizations'.
The terascale problems that are now emerging demand an understanding
of how to manage people and resources possibly distributed over many
sites. Evidence of the timely nature of this workshop can be seen at
this year's "Text Retrieval Conference" (TREC), which concluded with
the announcement of a new track next year which would be specifically
devoted to scaling information retrieval systems. This clearly
demonstrates the community need for scaling human language
technologies.
In order to address large scale speech and language problems that
arise in realistic tasks, we must address the issue of scalable
machine learning algorithms that can better exploit the structure of
such problems, their computational resource requirements and its
implications on how we carry out research as a community.
This workshop will bring researchers together who are interested in
meeting the challenges associated with scaling systems for natural
language processing. Topics include (but are not limited to):
+ exactly scaling existing techniques
+ applying interesting approximations which drastically reduce the
amount of required computation yet do not sacrifice much in the way
of accuracy
+ using on-line learning algorithms to learn from streaming data sources
+ efficiently retraining models as more data becomes available
+ experience with using very large datasets, apply for example Grid
computing strategies technologies
+ techniques for efficiently manipulating enormous volumes of data
+ human factors associated with managing large virtual organizations
+ adapting methods developed for dealing with large-scale problems
in other computational sciences, such as physics and biology, to natural
language processing
Invited Speaker:
TBA
Provisional program committee:
Chris Manning, Stanford University
Dan Roth, Univ of Urbana-Champaign
Ewan Klein, Univ of Edinburgh
Jun-ichi Tsujii, Tokyo University
Patrick Haffner, AT&T Research
Roger Evans, ITRI, Brighton
Steven Bird, Univ of Melbourne
Stephen Clark, Univ of Edinburgh
Thorsten Brants, Google
Walter Daelemans, Univ of Antwerp
Yann LeCun, New York University
John Carroll, Univ. of Sussex
Organizing Committee:
Miles Osborne, Univ of Edinburgh
Robert Malouf, San Diego State University
Srinivas Bangalore, AT&T Labs-Research
SUBMISSION FORMAT
Submissions must use the ACL latex style (available from the ACL 04 web
page). Paper submissions should consist of a full paper. The page
limit is eight pages. Reviewing will NOT be blind.
SUBMISSION PROCEDURE
Electronic submission only: send a gzipped postscript (preferred) or gzipped
PDF file with your submission to:
miles@inf.junk.ed.ac.uk *remove junk from address*
Please name the file with the surname of the first author (for example, "osborne.ps.gz") and in the subject line put "ACL 04 Workshop".
DEADLINES
Paper submission deadline: April 18th, 2004
Notification of acceptance for papers: April 30th, 2004
Camera ready papers due: May 15th, 2004
Wokshop date: Jul 26th, 2004
Contact Information:
Miles Osborne (miles@inf.junk.ed.ac.uk) *remove junk from address*
This archive was generated by hypermail 2b29 : Sun Jan 11 2004 - 17:19:17 MET