LINGUIST List 10.443

Thu Mar 25 1999

Calls: NLP/ACL, Tense Aspect & Mood

Editor for this issue: Karen Milligan <>

As a matter of policy, LINGUIST discourages the use of abbreviations or acronyms in conference announcements unless they are explained in the text.


  1. Andy Kehler, ACL Workshop on Unsupervised Learning for NLP
  2. Tim Stowell, CHRONOS: Conference on Tense, Aspect, & Mood Thermi

Message 1: ACL Workshop on Unsupervised Learning for NLP

Date: Wed, 24 Mar 1999 12:28:10 -0800
From: Andy Kehler <>
Subject: ACL Workshop on Unsupervised Learning for NLP


			ACL-99 Workshop
 Unsupervised Learning in Natural Language Processing

 University of Maryland, College Park, MD, USA
		 June 21st, 1999

 Endorsed by the Association for Computational Linguistics (ACL)
 Special Interest Group on Natural Language Learning (SIGNLL)


Many of the successes achieved from using learning techniques in
natural language processing (NLP) have utilized the supervised
paradigm, in which models are trained from data annotated with the
target concepts to be learned. For instance, the target concepts in
language modeling for speech recognition are words, and thus raw text
corpora suffice. The first successful part-of-speech taggers were
made possible by the existence of the Brown corpus (Francis, 1964), a
million-word data set which was laboriously hand-tagged a quarter of a
century prior. Finally, progress in statistical parsing required the
development of the Penn Treebank data set (Marcus et al. 1993), the
result of many staff years of effort. While it is worthwhile to
utilize annotated data when it is available, the future success of
learning for natural language systems cannot depend on a paradigm
requiring that large, annotated data sets be created for each new
problem or application. The costs of annotation are prohibitively
time and expertise intensive, and the resulting corpora are too
susceptible to restriction to a particular domain, application, or

Thus, long-term progress in NLP is likely to be dependent on the use
of unsupervised and weakly supervised learning techniques, which do
not require large annotated data sets. Unsupervised learning utilizes
raw, unannotated data to discover underlying structure giving rise to
emergent patterns and principles. Weakly supervised learning uses
supervised learning on small, annotated data sets to seed unsupervised
learning using much larger, unannotated data sets. Because these
techniques are capable of identifying new and unanticipated
correlations in data, they have the additional advantage of being able
to feed new insights back into more traditional lines of basic

Unsupervised and weakly supervised methods have been used successfully
in several areas of NLP, including acquiring verb subcategorization
frames (Brent, 1993; Manning, 1993), part-of-speech tagging (Brill,
1997), word sense disambiguation (Yarowsky, 1995), and prepositional
phrase attachment (Ratnaparkhi, 1998). The goal of this workshop is
to discuss, promote, and present new research results (positive and
negative) in the use of such methods in NLP. We encourage submissions
on work applying learning to any area of language interpretation or
production in which the training data does not come fully annotated
with the target concepts to be learned, including:

 * Fully unsupervised algorithms
 * `Weakly supervised' learning, bootstrapping models from small sets
 of annotated data 
 * `Indirectly supervised' learning, in which end-to-end task
 evaluation drives learning in an embedded language interpretation
 * Exploratory data analysis techniques applied to linguistic data
 * Unsupervised adaptation of existing models in changing environments
 * Quantitative and qualitative comparisons of results obtained with
 supervised and unsupervised learning approaches 

Position papers on the pros and cons of supervised vs. unsupervised
learning will also be considered.


Paper submissions can take the form of extended abstracts or full
papers, not to exceed six (6) pages. Authors of extended abstracts
should note the short timespan between notification of acceptance and
the final paper deadline. Up to two more pages may be allocated for
the final paper depending on space constraints. 

Authors are requested to submit one electronic version of their papers
*or* four hardcopies. Please submit hardcopies only if electronic
submission is impossible. Submissions in Postscript or PDF format are
strongly preferred.

If possible, please conform with the traditional two-column ACL
Proceedings format. Style files can be downloaded from

Email submissions should be sent to:

Hard copy submissions should be sent to:

 Andrew Kehler
 SRI International
 333 Ravenswood Avenue
 Menlo Park, CA 94025


Paper submission deadline: March 26
Notification of acceptance: April 16
Camera ready papers due: April 30


Andrew Kehler (SRI International)
Andreas Stolcke (SRI International)


Michael Brent (Johns Hopkins University)
Eric Brill (Johns Hopkins University)
Rebecca Bruce (University of North Carolina at Asheville)
Eugene Charniak (Brown University)
Michael Collins (AT&T Laboratories)
Marie desJardins (SRI International)
Moises Goldszmidt (SRI International)
Andrew Kehler (SRI International)
John Lafferty (Carnegie-Mellon University)
Lillian Lee (Cornell University)
Chris Manning (University of Sydney)
Andrew McCallum (Carnegie-Mellon University and Just Research)
Ray Mooney (University of Texas, Austin)
Srini Narayanan (ICSI, Berkeley)
Fernando Pereira (AT&T Laboratories)
David Powers (Flinders University of South Australia)
Adwait Ratnaparkhi (IBM Research)
Dan Roth (University of Illinois at Urbana-Champaign)
Andreas Stolcke (SRI International)
Janyce Wiebe (New Mexico State University)
Dekai Wu (Hong Kong University of Science and Technology)
David Yarowsky (Johns Hopkins University)
Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue

Message 2: CHRONOS: Conference on Tense, Aspect, & Mood Thermi

Date: Wed, 24 Mar 1999 12:25:46 -0800 (PST)
From: Tim Stowell <>
Subject: CHRONOS: Conference on Tense, Aspect, & Mood Thermi

 A Conference on Tense, Aspect, and Mood

The 1999 Thermi International Summer School in Linguistics, sponsored by
GLOW, will be hosting a conference on the syntax and semantics of tense,
aspect, and mood, to be held on July 16-17 1999. Thermi is located
approximately 10km from Mitilini, on the island of Lesbos, in Greece.

The conference will last for only two days, and each speaker will be
allotted approximately one hour so as to allow for a substantive
presentation and discussion period; consequently, we anticipate that it will
only be possible to accommodate around 15 speakers. All of these slots are
open; there will be no invited lectures. It is possible that funding will be
available to subsidize speakers' ground expenses in Thermi, though we expect
that speakers will have to find alternative funding sources to cover the
cost of air travel. (Further information about accommodation and funding
will be made available prior to the announcement of the program.)

The selection of papers for will be based on reviews of anonymous abstracts,
which are hereby solicited. Abstracts should be from one to two pages
long(double-spaced, no smaller than 10 pt font), including cited examples.
Authors are strongly encouraged to submit their abstracts by e-mail to
Sabine Iatridou at the following address:


Abstracts may also be submitted in hard-copy format, by mailing them to:

 Sabine Iatridou
 Linguistics and Philosophy
 MIT E39-236
 Cambridge, MA 02139 USA

The deadline for submission of abstracts is May 3, 1999. We expect to be
able to complete the reviews and announce the program by May 17.

In addition to the lectures, the conference will include a business 
meeting to discuss the possibility of establishing an international 
scholarly organization devoted to the promotion of scholarship on 
tense, aspect, mood, and related issues, which would be responsible
(among other things) for organizing a conference to be held at regular
intervals (either yearly or every other year). In recent years, there have
been several conferences dealing with these themes, including those held at
Cortona (1993), Tel Aviv (1993), Lake Arrowhead (1998), and Bergamo (1998).
In the most recent meetings, a number of participants have expressed a
desire to have a conference held at regular intervals, under the auspices 
of a scholarly society, rather than being sponsored solely by individual
universities on an ad hoc basis. We hope that the business meeting at 
Thermi will set the stage for bringing such plans to fruition.

Following the tradition established at Cortona, it is our hope that a wide
range of perspectives will be represented. However, given that the number
of papers presented at Thermi will be rather small, and given the relatively
short lead time, we recognize that many important research scholars working
in these areas may not be able to attend. For this reason, we invite all
researchers with an interest in such an organization to contact us in
advance, both to indicate their willingness to participate in such an
organization (in any capacity), and to provide written suggestions about 
the form that it should take.

Questions about the Thermi conference, including the abstact guidelines, 
as well as suggestions about the proposed scholarly organization, should 
be sent to Tim Stowell at the following e-mail address:

or at the following mailing address:

 c/o Tim Stowell
 UCLA Linguistics Dept.
 405 Hilgard Ave.
 Los Angeles, CA, 90095-1543

Tim Stowell
Dept. of Linguistics, UCLA, Los Angeles, CA 90095-1543
Telephone: 1-310-825-0634; Fax: 1-310-206-5743.
Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue