* * * * * * * * * * * * * * * * * * * * * * * *
LINGUIST List logo Eastern Michigan University Wayne State University *
* People & Organizations * Jobs * Calls & Conferences * Publications * Language Resources * Text & Computer Tools * Teaching & Learning * Mailing Lists * Search *
* *
LINGUIST List 18.1120

Thu Apr 12 2007

Calls: Computational Ling/USA; Computational Ling/Netherlands

Editor for this issue: Ania Kubisz <anialinguistlist.org>

As a matter of policy, LINGUIST discourages the use of abbreviations or acronyms in conference announcements unless they are explained in the text. To post to LINGUIST, use our convenient web form at http://linguistlist.org/LL/posttolinguist.html.
        1.    Emily Bender, Grammar Engineering across Frameworks 2007
        2.    Sophia Katrenko, Machine Learning for Natural Language Processing

Final Standing: Top 5 Schools in LL Grad School Challenge:
1. Stanford University $3270
2. University of Massachusetts at Amherst $2027
3. University of Arizona $1835
4. University of Washington $1474
5. University of California, Santa Barbara $1006
To see the full list, go to: http://linguistlist.org/donation/fund-drive2007/allschools.cfm


Message 1: Grammar Engineering across Frameworks 2007
Date: 11-Apr-2007
From: Emily Bender <ebenderu.washington.edu>
Subject: Grammar Engineering across Frameworks 2007

Full Title: Grammar Engineering across Frameworks 2007
Short Title: GEAF07

Date: 13-Jul-2007 - 15-Jul-2007
Location: Stanford, CA, USA
Contact Person: Emily M. Bender
Meeting Email: geaf-organizersu.washington.edu
Web Site: http://www-csli.stanford.edu/~thking/GEAF07.html

Linguistic Field(s): Computational Linguistics

Call Deadline: 30-Apr-2007

Meeting Description:
This workshop aims to bring together grammar engineers from different frameworks
to compare research and methodologies, particularly around the themes of
evaluation, modularity, maintainability, relevance to theoretical and
computational linguistics, and evaluation for internal purposes.

Call for Papers
Deadline extended to 4/30/07
Grammar Engineering across Frameworks
July 13-15, 2007
Stanford, California, USA

This workshop is part of the 2007 LSA Summer Institute. (But note that workshop
attendees do not have to register for the Institute.)

Recent years have seen the development of techniques and resources to support
robust, deep grammatical analysis of natural language in real-world domains and
applications. The demands of these types of tasks have resulted in significant
advances in areas such as parser efficiency, hybrid statistical/symbolic
approaches to disambiguation, and the acquisition of large-scale lexicons. The
effective development, maintenance and enhancement of grammars is a central
issue in such efforts, and the size and complexity of realistic grammars forces
these processes to be tackled in ways that have much in common with software
engineering. This workshop aims to bring together grammar engineers from
different frameworks to compare their
research and methodologies.

Panel Discussion on Evaluation: How can we develop evaluation
methodologies and metrics which can capture the added benefits of deep
linguistic analysis?

Mary Dalrymple, Oxford University (moderator)
Roger Levy, University of California, San Diego
Stephan Oepen, University of Oslo
Martha Palmer, University of Colorado, Boulder

Paper Topics:
The workshop is soliciting submissions for papers on the following

1. Evaluation: Proposals concerning evaluation methodologies and metrics which
can capture the added benefits of deep linguistic analysis; evaluation
techniques which can compare grammars across varieties/languages

2. Modularity: Reflections on which aspects of linguistic structure can most
easily be separated out from each other, why and how the analyses of separate
linguistic phenomena are interconnected/interdependent, and the role of
frameworks on promoting or inhibiting modularity

3. Maintainability: Techniques for improving long-term and multideveloper
maintainability of grammars; impacts of considerations of maintainability on
choices of linguistic analysis

4. Relevance to theoretical and computational linguistics: Reflections on
how to present grammar engineering work to other research communities.

5. Regression testing: Evaluation for internal purposes; methodologies and
techniques for test suite construction, role of test suites in day-to-day
progress on grammars

Organizing Committee:
Emily M. Bender, University of Washington
Tracy Holloway King, PARC

Program Committee:
Jason Baldridge
Srinivas Bangalore
John Bateman
Miriam Butt
Aoife Cahill
Stephen Clark
Berthold Crysmann
Steffi Dipper
Dan Flickinger
Ron Kaplan
Montserrat Marimon
Owen Rambow
Jesse Tseng

Important Dates and Submission Details:

Abstracts due: April 30, 2007
Notification of acceptance: May 11, 2007
Demo session requests due: June 1, 2007
Workshop: 13-15 July, 2007

Submissions are to take the form of 4 (four) page extended abstracts,
in PDF format, with 12 point font.

Please submit your papers directly to:


Contact for inquiries:

geaf-organizers at u dot washington dot edu

Special Demo Session:
In addition to the panel and papers, there will be a demo session. If you wish
to give a demonstration of a system relevant to the ''Grammar Engineering Across
Frameworks'' theme, please submit a title of the demo and a one-paragraph
description through Easy Chair, by June 1, 2007. You do not have to have a
paper in the workshop in order to give a demo.

We plan to publish the proceedings (full papers) as an online volume
through CSLI publications after the workshop.
Message 2: Machine Learning for Natural Language Processing
Date: 11-Apr-2007
From: Sophia Katrenko <katrenkoscience.uva.nl>
Subject: Machine Learning for Natural Language Processing

Full Title: Machine Learning for Natural Language Processing
Short Title: ML4NLP

Date: 16-May-2007 - 16-May-2007
Location: Amsterdam, Netherlands
Contact Person: Sophia Katrenko
Meeting Email: benelearn07science.uva.nl
Web Site: http://www.science.uva.nl/~katrenko/benelearn07/workshop.html

Linguistic Field(s): Computational Linguistics

Call Deadline: 29-Apr-2007

Meeting Description:

Workshop: Machine Learning for Natural Language Processing, Amsterdam, NL

Call for Posters

Human-Computer Studies Laboratory of the University of Amsterdam organizes the
workshop ''Machine Learning for Natural Language Processing'' to be held on May
16, 2007 in Amsterdam. The workshop is collocated with the annual Belgian-Dutch
conference on Machine Learning (Benelearn'07).

We invite submissions of extended abstracts on topics regarding the application
of machine learning to natural language processing. The topics of interest
include (but are not limited to):

- ML applied to various NLP tasks (syntax and semantics)
- Supervised, semi-supervised and unsupervised techniques for NLP
- Language acquisition
- Information extraction
- Relational learning
- Ontology learning and enrichment
- Learning with the background knowledge

Program (speakers)

Rens Bod (University of St. Andrews, UK and University of Amsterdam, the
''Is the End of Supervised NLP in Sight?''

Veronique Hoste (University of Ghent, Belgium)
''Framing Discourse as a Classification Approach''

Kai-Uwe Kuehnberger (University of Osnabrueck, Germany)
''Extraction and Adaptation of Ontological Knowledge from Heterogeneous Data

Claire Nedellec (Laboratoire Mathematique Informatique et Genome, France)
''Alvis Semantic Search Engine Adaptation to Biology''

Sander Canisius (Tilburg University, the Netherlands)
''Memory, Language, and Semantics; Machine Learning for Natural Language in

David Ahn, Maarten de Rijke, Wouter Weerkamp (University of Amsterdam, the
''Learning to Track Sentiments in Text Streams: The Verdonk Case''

Jakub Zavrel (Textkernel, the Netherlands) TBA

Submission procedure:

Submissions should not exceed two (2) pages (the template can be downloaded from
http://www.science.uva.nl/~katrenko/benelearn07/instructions.tar.gz ). Please
send your submission to benelearn07science.uva.nl with a subject line ''ML4NLP
submission''. Accepted abstracts will be published as the workshop notes.

Important dates:

Submission deadline: April 29, 2007
Notification of acceptance: May 5, 2007
Registration due: May 5, 2007
Workshop: May 16, 2007

Contact information: benelearn07science.uva.nl

This Year the LINGUIST List hopes to raise $55,000. This money will go to help keep the 
List running by supporting all of our Student Editors for the coming year.

See below for donation instructions, and don't forget to check out our Fund Drive 2007 
LINGUIST List Superhero Adventure for some Fund Drive fun!


There are many ways to donate to LINGUIST!

You can donate right now using our secure credit card form.

Alternatively you can also pledge right now and pay later.

For all information on donating and pledging, including information on how to donate by 
check, money order, or wire transfer, please visit:


The LINGUIST List is under the umbrella of Eastern Michigan University and as such can 
receive donations through the EMU Foundation, which is a registered 501(c) Non Profit 
organization. Our Federal Tax number is 38-6005986. These donations can be offset against 
your federal and sometimes your state tax return (U.S. tax payers only). For more 
information visit the IRS Web-Site, or contact your financial advisor.

Many companies also offer a gift matching program, such that they will match any gift 
you make to a non-profit organization. Normally this entails your contacting your human 
resources department and sending us a form that the EMU Foundation fills in and returns 
to your employer. This is generally a simple administrative procedure that doubles the 
value of your gift to LINGUIST, without costing you an extra penny. Please take a moment 
to check if your company operates such a program.

Thank you very much for your support of LINGUIST!


Respond to list|Read more issues|LINGUIST home page|Top of issue

Please report any bad links or misclassified data

LINGUIST Homepage | Read LINGUIST | Contact us

NSF Logo

While the LINGUIST List makes every effort to ensure the linguistic relevance of sites listed
on its pages, it cannot vouch for their contents.