LINGUIST List 11.2508

Tue Nov 21 2000

Calls: Natural Lang Engineering, Student Research

Editor for this issue: Jody Huellmantel <jodylinguistlist.org>


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

Directory

  1. Beverly Nunan, Special Issue in the Journal of Natural Langugage Engineering
  2. Christof Monz, ACL/EACL 2001 - Student Research Workshop

Message 1: Special Issue in the Journal of Natural Langugage Engineering

Date: Sun, 19 Nov 2000 09:56:24 -0500
From: Beverly Nunan <bnunanmitre.org>
Subject: Special Issue in the Journal of Natural Langugage Engineering



CALL FOR PAPERS

NATURAL LANGUAGE ENGINEERING
 
 SPECIAL ISSUE ON QUESTION ANSWERING
 
 Guest editors:
 Lynette Hirschman (MITRE)
 Robert Gaizauskas (University of Sheffield)
 
 
 As users struggle to navigate the wealth of on-line information now
 available, the need for automated question answering systems becomes
 more urgent: specifically, for systems that would allow a user to ask a
 question in everyday language and get the answer quickly, with back-up
 material available on demand. Question answering has become, over the
 past several years, a major focus of research activity. This Call for
 Papers solicits submissions that discuss the performance, the
 requirements, the uses, and the challenges of question answering
 systems.

 Question answering systems provide a rich research area. To answer a
 question, a system must analyze the question, perhaps in the context of
 some ongoing interaction; it must find one or more answers by consulting
 
 on-line resources; and it must present the answer to the user in some
 appropriate form, perhaps associated with justification or supporting
 materials.
 
 Several conferences and workshops have focused on aspects of the
 question answering research area. For the past two years, the Text
 Retrieval Conference (TREC) (http://trec.nist.gov) has sponsored a
 question-answering track which has evaluated systems that answer factual
 questions based on finding answer strings in the TREC corpus, using both
 information retrieval and natural language processing techniques. A
 focus on reading comprehension provides a different approach to question
 answering, evaluating systems' ability to answer questions about a
 specific reading passage. These kinds of tests are used to evaluate
 students' comprehension, providing a basis for comparing system
 performance to human performance. This was the subject of a Johns
 Hopkins Summer Workshop,
 http://www.clsp.jhu.edu/ws2000/groups/reading/prj_desc.shtml
 
 Both of these research areas have had to address a number of difficult
 questions:
 � How can question answering systems be evaluated? Do we have to have
 human graders, or can we find automated ways of grading short answer
 tests that approximate human graders closely enough?
 � How should questions and answers be classified? Should classifications
 be based on linguistic features of questions and answers? On the types
 and sources of knowledge used to derive answers? On the types of
 processing required to derive answers?
 � What makes a question hard? Can we define linguistic features that
 help to predict question difficulty?
 � Can we identify different classes of users of question answering
 systems, and if so, what are their different requirements?
 � What makes an answer good? Should answers be short? Long? What about
 sentence extracts compared to generated text? What about summaries?
 � What is the best way to present answers to a user? How much context
 and justification is appropriate? How much drill down needs to be
 supported?
 � Do question answering systems need to build models of users' knowledge
 states to generate appropriate answers? How can this process be managed?

 � What are reasonable expectations for question answering systems:
 providing factual answers found literally in texts, providing factual
answers inferred from texts, providing summaries of multiple sources,
 providing analysis?
 � How does the performance of systems compare to the performance of
 people? Can such systems complement people? Teach people? Replace
 people?
 � Is it possible to create domain-independent question answering
 systems, or is it critical to restrict the domain of such a system to a
 specific topic area? What are the trade-offs in terms of performance?
 � Can a question answering system use spoken input? Can it retrieve
 information from spoken "documents" such as news stories or interviews?
 What are the performance penalties when dealing with the additional
 uncertainty that characterizes speech or OCR?
 
 
 We invite submission of papers addressing any of these questions, or
 other issues related to the creation, evaluation, or deployment of
 question answering systems. We also encourage submissions that address
 infrastructure issues, such as tools for building question answering
 systems, for collecting corpora, or for annotating collections.
 
 Submission Information
 
 Submit full papers of no more than 25 pages (exclusive of references),
 twelve point, double-spaced, with one inch margins before the initial
 submission deadline. Submissions not conforming to these guidelines will
 not be reviewed.
	 
 Email submission is preferred, and should be directed to the special
 issue editors at the email address: lynettemitre.org. The subject line
 should read: JNLE QA Submission. Preferred email submission formats are:
 
 Word, PostScript, PDF, or plain text (for papers without complex
 figures, etc).
 
 If email submission is not possible, then five copies of the paper
 should be mailed to:
 
 Dr. Lynette Hirschman
 The MITRE Corporation 3K-157
 202 Burlington Rd.
 Bedford, MA 01730
 USA
 
 Phone: 781-271-7789
 Fax: 781-271-2352
 
 Mailed submissions must arrive on or before the deadline for submission.
 
 Submission Dates
 
 * Submissions are due on February 26, 2001
 * Notification of acceptance will be given by April 23, 2001.
 * Camera-ready copy due July2, 2001
 * Publication: Fall-Winter 2001
 
	
	
Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue

Message 2: ACL/EACL 2001 - Student Research Workshop

Date: Sun, 19 Nov 2000 21:02:34 +0100
From: Christof Monz <christofscience.uva.nl>
Subject: ACL/EACL 2001 - Student Research Workshop


 Call for Papers 

 Student Research Workshop 
 at the joint ACL/EACL 2001 Meeting

 July 6-11, 2001
 Toulouse, France 

 submission deadline: February 12, 2001 

The information below can also be found at this URL: 
www.science.uva.nl/~christof/acl01-student/ 

Note: The exact dates of the Workshop have not been firmly established
yet. Tentatively, the Workshop may take place anytime between 6th and
11th of July, 2001.

1. General Invitation for Submissions 

The Student Research Workshop is an established tradition at ACL
conferences. The main purpose of the workshop is to provide a forum
for student researchers who are investigating various areas related to
Computational Linguistics and Natural Language Processing. We would
like to invite student researchers to submit their work to the
workshop. Seeing that the main mission of the student workshop is to
provide the participants with a wide audience and useful feedback, the
emphasis of the workshop will be on work in progress. For the Student
Workshop, original, and unpublished research is invited on all aspects
of computational linguistics, including, but not limited to these
topic areas:

 - pragmatics 
 - discourse 
 - semantics 
 - syntax and the lexicon 
 - phonetics 
 - phonology and morphology 
 - interpreting and generating spoken and written language 
 - linguistic, mathematical and psychological models of language 
 - language-oriented information retrieval and information extraction
 - corpus-based language modeling 
 - machine translation and translation aids 
 - natural language interfaces and dialogue systems 
 - approaches to coordinating the linguistic with other modalities in 
 multi-media systems 
 - message and narrative understanding systems 

The main conference will also feature tutorials, workshops, and demos.
See the Main ACL/EACL 2001 page for information: 
http://www.irit.fr/ACTIVITES/EQ_ILPL/aclWeb/acl2001.html

2. Submission Requirements 

Papers should describe original work in progress. The main purpose of
presenting at the workshop is to exchange ideas with other researchers
and to receive helpful feedback for further development of the
work. Papers should clearly indicate directions for future research
wherever appropriate. The papers can have more than one author;
however, all authors MUST be students. A paper accepted for
presentation at the Student Workshop cannot be presented or have been
presented at any other meeting with publicly available published
proceedings. Papers that are being submitted to other conferences must
indicate this immediately after the title material on the first page.

3. Submission Procedure 

Paper Registration 
 
Registration of your submission is required. This can be done by
filling out a form available at the web site of the workshop:
http://www.science.uva.nl/~christof/acl01-student/ 

After you fill out and submit this form, a unique ID number will be
generated and sent to you in an e-mail shortly after the paper
registration. You will then be able to use this ID number instead of
your name on the title page of the paper and in any subsequent
correspondence with the workshop co-chairs.

If you are unable to use the on-line form for paper registration or
experience problems using it, please, send email to
acl01-studentscience.uva.nl

Submission format

Submissions should follow the two-column format of ACL proceedings and
should not exceed six (6) pages, including references. We strongly
recommend the use of ACL latex style files or Microsoft Word Style
files tailored for this year's conference. These will soon be
available from the web site:
http://www.science.uva.nl/~christof/acl01-student/

These style files allow for a graceful transition to the style
required for publication. A description of the format will also be
available in case you are unable to use these style files directly.

Separate items to be submitted 

Identification page 
Title: 
Paper ID code: (generated at paper registration) 
Author(s) name(s) affiliation and e-mail addresses 
Topic Area: (one or two general topic areas) 
Keywords: Up to 5 keywords specifying the subject area 
Under Consideration for Other Conferences: (if yes, please specify) 

Abstract: short summary (up to 5 lines) 
Title page 
Title: 
Paper ID code: (generated at paper registration) 
Topic Area: (one or two general topic areas) 
Keywords: Up to 5 keywords specifying the subject area 
Under Consideration for Other Conferences: (if yes, please specify) 

Abstract: short summary (up to 5 lines) 

Paper 

Electronic submissions as well as hard copy submissions are
acceptable.

Electronic Submissions 

If you are submitting your paper electronically, only the following
formats will be acceptable:
 - PostScript (.ps) 
 - Rich Text Format ACL style (.rtf) 
 - Microsoft Word ACL style(.doc) 
 - PDF (.pdf) 

Electronic submissions should be sent in an attachment to the
following e-mail address: acl01-studentcis.upenn.edu

If you are submitting a hard copy of your paper, please send six
double sided copies of your paper (two copies should have the
identification page attached, four should have the title page
attached) to the following address:

Eleni Miltsakaki
Institute of Research in Cognitive Science
Suite 400A, 3401 Walnut St.
University of Pennsylvania
Philadelphia, PA 19104-6228
USA

4. Reviewing Procedure 

Reviewing of papers submitted to the Student Workshop will be managed
by the Student Workshop Co-Chairs, each of whom will have the
assistance of a team of reviewers. Each submission will be matched
with a mixed panel of student and senior researchers for review. The
final acceptance decision will be made based on the results of the
review.

Note that reviewing of papers will be blind; therefore, please, make
sure you do not put the author(s) name(s) on the title page. (See
paper submission requirements for details). You should not have any
self-identifying references anywhere in the paper submitted for
review. For example, you can't have a reference like this "We showed
previously (Smith, 1991), ..." Instead, use citations such as "Smith
previously showed (Smith, 1991)..."

5. Schedule 

Submissions must be received by February 12th, 2001. Late submissions
(those arriving on or after February 13th, 2001) will be automatically
disqualified. The student workshop committee is not responsible for
postal delays or other mailing problems. For electronic submissions,
all time zones will be taken into account) Acknowledgment will be
emailed soon after receipt. Notification of acceptance will be sent
to authors (by email) on April 20th, 2001. Detailed formatting
guidelines for the preparation of the final camera-ready copy will be
provided to authors with their acceptance notice.

6. Timetable 

Important Dates: 

Paper registration: February 5, 2001
Paper submission deadline: February 12, 2001 
Notification of Acceptance: April 20, 2001 
Camera-Ready Copy Due: May 18, 2001 

7. Contact Information 

If you need to contact the Co-Chairs of the Student Workshop, please
use: acl01-studentscience.uva.nl
An e-mail sent to this address will be forwarded to all Co-Chairs.

Eleni Miltsakaki (Co-Chair)
Institute of Research in Cognitive Science
Suite 400A, 3401 Walnut St.
University of Pennsylvania
Philadelphia, PA 19104-6228, USA
E-mail: elenimilinc.cis.upenn.edu
Phone: +1 215 573-6283
Fax: +1 215 573-9247

Christof Monz (Co-Chair)
Institute for Logic, Language and Computation (ILLC)
University of Amsterdam
Plantage Muidergracht 24
1018 TV Amsterdam, The Netherlands
E-mail: christofscience.uva.nl
Phone: +31 20 525-6095
Fax: +31 20 525-5101

Ant�nio Ribeiro (Co-Chair)
Universidade Nova de Lisboa
Faculdade de Ci�ncias e Tecnologia
Departamento de Inform�tica
Quinta da Torre
P-2825-114 Caparica, Portugal
E-mail: ambardi.fct.unl.pt
Phone: +351 21 294-8300, ext. 10743
Fax: +351 21 294-8541
Mail to author|Respond to list|Read more issues|LINGUIST home page|Top of issue