Conf: 3 conferences

alexis nasr alexis.nasr at
Tue Mar 6 17:43:46 UTC 2001

1/  2001 Conference on Empirical Methods in Natural Language Processing
(includes submission instructions; note notification deadline)

2/    ***********PRELIMINARY CALL FOR PARTICIPATION*******************
Language Technologies 2001:
Second Meeting of the North American Chapter
of the Association for Computational Linguistics

third workshop on


(includes submission instructions; note notification deadline)

2001 Conference on Empirical Methods in Natural Language Processing

Sponsored by SIGDAT and the Intelligent Information Systems Institute

SIGDAT, the Association for Computational Linguistics' special
interest group on linguistic data and corpus-based approaches to NLP,
invites submissions to EMNLP 2001.  The conference will be held at
Carnegie Mellon University, Pittsburgh, PA USA on June 3 and 4,
immediately preceding the meeting of the North American Chapter of the

We are interested in papers from academia, government, and industry on
all areas of traditional interest to the SIGDAT community and aligned
fields, including but not limited to:

* information extraction
* information retrieval
* language and dialog modeling
* lexical acquisition
* machine translation
* multilingual technologies
* question answering
* statistical parsing
* summarization
* tagging
* term and named-entity extraction
* word sense disambiguation
* word, term, and text segmentation

Also, to encourage reflection on the current state of the art in
corpus-based methods, the conference will have the following theme:

  "What Works and What Doesn't:  Successes and Challenges"

Successes --- We solicit papers showing the success of empirical
methods in and across application settings.  Examples include
improvements in information retrieval performance due to employing
language modeling techniques; effective use of statistical word
segmentation algorithms in machine translation systems; and increased
speech recognition accuracy through the incorporation of statistical

Challenges --- It is clear that empirical and corpus-based methods
have enjoyed many successes over the past years; but in looking to
future accomplishments, the community needs to be aware of the
limitations of various techniques and paradigms.  We welcome papers
that carefully expose and study such limitations. Examples include the
identification and exploration of: classes of domains or problems in
which popular techniques perform poorly; significant gaps between
human and machine performance on tasks where statistical approaches
have made great progress; and important practical situations where
common assumptions fail to hold.  *** We emphasize that we seek
submissions that thoughtfully document fundamental limitations, rather
than simply report on unsuccessful experiments. *** It is desired that
such papers contain thorough examination, via careful experimentation,
of the critical factors contributing to the "negative" result.


Requirements: Submissions must describe original, completed,
unpublished work, and include concrete evaluation results when
appropriate.  Papers being submitted to other meetings must provide
this information (see submission format); in the event of multiple
acceptances, authors are requested to immediately notify the EMNLP
program chair (llee at and choose which meeting to
present and publish the work at as soon as possible --- EMNLP cannot
accept for publication or presentation work that will be (or has been)
published elsewhere.

Submission Format: Submissions must be hardcopy, and consist of full
papers of not more than 3200 words (exclusive of references).  Authors
are strongly encouraged to use the LaTeX style files or MSWord
equivalents available from the EMNLP website -- these formats will
ease the transition to the proceedings version.

Reviewing will be blind. No information identifying the authors should
be in the paper: this includes not only the authors' names and
affilations, but also self-references that reveal authors' identities;
for example, "We have previously shown (Smith 1999)" should be changed
to "Smith (1999) has previously shown".  A separate identification
page is required: see below.

Submission procedure: First, an electronic notice of intent to submit
is required.  Please email llee at
(subject line EMNLP 2001 ITS) by March 9 with the following information:

    Paper title
    Authors' names, affiliations, and email addresses
    Contact author
    A short list of keywords
    A short (no more than 5 lines) summary of the contents
    Whether or not the paper is under consideration for other conferences
      (please specify)

Then, six hardcopies of the paper together with a single separate
page listing *all* the information from the notice of intent to
submit (i.e., title, authors, contact author, keywords, summary, and
multiple-submission information -- a printout of the notice of intent
to submit suffices) must be received by March 13 at the
following address:

    EMNLP 2001 Submissions
    Lillian Lee
    4130 Upson Hall
    Cornell University
    Ithaca, NY 14853-7501

The EMNLP committee is not responsible for postal delays or other mail
problems.  Papers will not be accepted electronically, and submissions
that do not conform to the guidelines above are subject to rejection
without review.


Notification deadline:     March 9, 2001
Submission deadline:       March 13, 2001
Acceptance notification:   April 13, 2001
Camera-ready copy due:     May 3, 2001
Conference:                June 3-4, 2001


Lillian Lee (chair), Cornell University, llee at
Donna Harman (co-chair), NIST, donna.harman at


   ***********PRELIMINARY CALL FOR PARTICIPATION*******************

                Language Technologies 2001:

         Second Meeting of the North American Chapter
      of the Association for Computational Linguistics

                    June 2-7, 2001
               Carnegie Mellon University
              Pittsburgh, Pennsylvania, USA

   ***********PRELIMINARY CALL FOR PARTICIPATION*******************

The second meeting of the North American Chapter of the Association
for Computational Linguistics will be held at Carnegie Mellon
University, June 2-7, 2001.  We have a diverse selection of tutorials,
workshops, talks, and exhibits, not to mention a fun opening picnic
and a banquet in the grand and elegant Carnegie Museum of Natural
History.  We will be joined by EMNLP (June 3 and 4) and the Workshop
on Language Modelling and Information Retrieval (May 31-June 1).  The
conference also features CD ROM proceedings, wireless internet access
throughout the CMU campus (please register your WaveLAN device in
advance), email room, and ethernet connections for laptops.  While you
are in Pittsburgh, don't miss the Three Rivers Arts Festival (June
1-17) featuring visual arts, artists market, and over 100 free


    Early registration (on line or by mail): March 15-April 30
    Late registration  (on line or by mail): May 1-26
    On site registration: June 2-7

    Regular ACL member     $250 (early)  $300 (late, on location)
    Regular Non-ACL member $310 (early)  $370 (late) - includes ACL memb dues
    Student ACL member     $100 (early)  $125 (late)
    Student Non-ACL member $130 (early)  $155 (late) - includes ACL memb dues

    Workshops (each, 1 day)    $50 (early)   $75 (late)
    EMNLP (2 days)            $100 (early)  $150 (late)
    Tutorials (each, 1/2 day) $100 (early)  $125 (late)
               student         $75 (early)  $100 (late)

    Banquet tickets            $65 (regular) $40 (student)

***************** PRELIMINARY PROGRAM ************************


    "How May I Help You?": Automated Customer Service via Natural
    Spoken Dialog.
    Alicia Abella, Allen Gorin, Guiseppe Riccardi, Tirso Alonso,
    Jerry Wright, AT&T Shannon Laboratory

    Empirical Methods in Natural Language Processing:
    What's Happened Since the First SIGDAT Meeting?
    Kenneth Ward Church, AT&T Labs-Research

    Building Synthetic Voices.
    Alan W Black and Kevin A. Lenzo, Carnegie Mellon University

    Open-Domain Textual Question Answering.
    Sanda Harabagiu and Dan Moldovan, Southern Methodist University

WORKSHOPS, June 3 and 4
Please see the web site (
for individual submission deadlines.

 Sunday, June 3

    Automatic Summarization,
    Jade Goldstein and Chin-Yew Lin, co-chairs

    Workshop on MT Evaluation: Hands-On Evaluation
    Eduard Hovy and Florence Reeder, co-chairs

    WordNet and Other Lexical Resources:
    Applications, Extensions and Customizations (Day 1)
    Dan Moldovan, Sanda Harabagiu, Wim Peters, Mark Stevenson, and
    Yorick Wilks, co-chairs

 Monday, June 4

    Student Research Workshop
    Krzysztof Czuba and Lisa Michaud, co-chairs

    Adaptation in Dialogue Systems,
    Cindi Thompson, Tim Paek, and Eric Horvitz, co-chairs

    WordNet and Other Lexical Resources:
    Applications, Extensions and Customizations (Day 2)
    Dan Moldovan, Sanda Harabagiu, Wim Peters, Mark Stevenson, and
    Yorick Wilks, co-chairs

Deadline for submissions, March 13

DEMOS, June 5-7
Deadline for submissions, March 2

A highlight of this year's conference will be the prominent role given to
industrial sponsors and exhibitors, aimed at attracting the latest commercial
trends in language technology. A number of companies have already signed up to

EXHIBITORS (to date):
    Multicorpora R&D Inc.
    Trados Corporation

SPONSORS (to date):



    Mitsubishi Electric Research Labs
    SRA, International

Pending and new exhibitors and sponsors, please contact Lynn Carlson
(lmcarls at or Kurt Godden (kgodden at


 Invited Speakers:
    Tom Mitchell, Carnegie Mellon University

    Other invited speakers to be announced.

 Natural Language Generation

    Instance-Based Natural Language Generation (Sebastian Varges,
    Chris Mellish)
    Corpus-based NP Modifier Generation (Hua Cheng, Massimo Poesio,
    Renate Henschel, Chris Mellish)
    A Trainable Sentence Planner (Marilyn A. Walker, Owen C. Rambow,
    Monica Rogati)

 Information Retrieval and Machine Learning

    Why Inverse Document Frequency? (Kishore Papineni)
    Question Answering Using Maximum-Entropy Components (Abraham
    Ittycheriah, Martin Franz, Wei-Jing Zhu, Adwait Ratnaparkhi)
    Transformation Based Learning in the Fast Lane (Grace Ngai, Radu


    Identifying User Corrections Automatically in Spoken Dialogue Systems
    (Julia Hirschberg, Diane Litman, Marc Swerts)
    Learning Optimal Dialogue Management Rules by Using Reinforcement
    Learning and Inductive Logic Programming (Renaud Lecoeuche)

 Word Meaning

    A Corpus-based Account of Regular Polysemy: The Case of
    Context-Sensitive Adjectives (Maria Lapata)
    Tree-Cut and a Lexicon Based on Systematic Polysemy (Noriko Tomuro)
    A Decision Tree of Bigrams is an Accurate Predictor of Word Sense (Ted


    An Algorithm for Aspects of Semantic Interpretation Using an Enhanced
    WordNet (Fernando Gomez)
    Class-Based Probability Estimation Using a Semantic Hierarchy
    (Stephen Clark, David Weir)
    Identifying Cognates by Phonetic and Semantic Similarity (Grzegorz

 Speech Synthesis and Recognition

    Re-engineering Letter-to-Sound Rules (Martin Jansche)
    Edit Detection and Parsing for Transcribed Speech (Eugene Charniak
    and Mark Johnson)
    Generating Training Data for Medical Dictations (Sergey Pakhomov,
    Michael Schonwetter, Joan Bachenko)

 Machine Translation

    A Finite-State Approach to Machine Translation (Srinivas Bangalore,
    Giuseppe Riccardi)
    Information-Based Machine Translation (Keiko Horiguchi)
    Multipath Translation Lexicon Induction (Gideon S. Mann and David


    A Probabilistic Earley Parser as a Psycholinguistic Model (John
    Refining Tabular Parsers for TAGs (Eric Villemonte de la Clergerie)
    Applying Co-Training Methods to Statistical Parsing (Anoop Sarkar)
    Refining Tabular Parsers for TAGs (Eric Villemonte de la Clergerie)

 Language Modeling

    A Structured Language Model Based on Context-Sensitive
    Probabilistic Left-Corner Parsing
    (Dong Hoon Van Uytsel, Dirk Van Compernolle, Filip Van Aelten)
    Do CFG-Based Language Models Need Agreement Constraints?
    (Manny Rayner, Genevieve Gorrell, Beth Ann Hockey, John Dowding,
    Johan Boye)
    Naive Bayes Detection of Non-Native Utterances (Laura Mayfield
    Tomokiyo, Rosie Jones)

 Names and Coreference

    Unsupervised Learning of Name Structure From Coreference Data (Eugene
    Text and Knowledge Mining for Coreference Resolution (Sanda Harabagiu,
    Razvan Bunescu, Steve Maiorano)

 Chunking and Morphology

    Knowledge-Free Induction of Inflectional Morphologies (Patrick
    Schone, Daniel Jurafsky)
    Chunking with Support Vector Machines (Taku Kudo, Yuji Matsumoto)
    Inducing Multilingual POS Taggers and NP Bracketers via Robust
    Projection Across Aligned Corpora (David Yarowsky, Grace Ngai)


    General Chair, Lori Levin
    Program, Kevin Knight
    Local Arrangements, Alon Lavie
    Tutorials, Dekang Lin
    Workshops, Lillian Lee
    Student Workshop, Lisa Michaud and Krzysztof Czuba
    Student Workshop Advisor, Deborah Dahl
    Demos, Ronnie Smith
    Exhibits, Lynn Carlson
    Sponsorships, Kurt Godden
    Publicity, Ralf Brown
    Web Master, Bob Frederking

    Eric Brill
    Ann Copestake
    Marti Hearst
    Aravind Joshi
    Andrew Kehler
    Elliot Macklovitch
    Fernando Pereira
    Owen Rambow
    Elizabeth Shriberg
    Ralph Weischedel

                  * THIRD CALL FOR PAPERS *

                     third workshop on



                Siena, Italy, June 18-20, 2001

              (Submission deadline: March 15, 2001)


Traditional inference tools (such as theorem provers and model
builders) are reaching new levels of sophistication and are now widely
and easily available. A wide variety of new tools (statistical and
probabilistic methods, ideas from the machine learning community) are
likely to be increasingly applied in computational semantics. Most
importantly of all, computational semantics seems to have reached the
stage where the exploration and development of inference is one of its
most pressing tasks - and there's a lot of interesting new work which
takes inferential issues seriously.

The Workshop on Inference in Computational Semantics (ICoS) intends to
bring researchers from areas such as Computational Linguistics,
Artificial Intelligence, Computer Science, and Logic together, in
order to discuss approaches and applications of Inference in natural
language semantics.

ICoS-1 took place in Amsterdam on August 15, 1999 with an attendance
of over 50 researchers. A selection of the papers presented at ICoS-1
has been published in a special issue of the Journal of Language and

ICoS-2 took place in Dagstuhl Castle, Germany, on July 29-30,
2000. Although the attendance was only 30, it was an intense and
communicative meeting. A selection of the papers presented at ICoS-2
will be published in the Journal of Language and Computation.

ICoS-3 will be co-located with the the International Joint Conference
on Automated Reasoning (IJCAR 2001, which takes place June 18-23, 2001
at Siena, Italy. IJCAR is a joint meeting of all major conferences on
automated theorem proving (CADE, FTP, TABLEAUX), and is therefore a
good chance to meet the theorem proving community.

ICoS-3 is endorsed by SIGSEM, the Association for Computational
Linguistics (ACL) Special Interest Group (SIG) on computational

People who would like to submit a paper, system descriptions or who
would like to attend the workshop should consider the following dates:

     Submission Deadline: March 15, 2001.
     Notification: April 15, 2001.
     Final Versions: May 15. 2001.
     Early Registration until: June 1., 2001.
     ICoS-3 Tutorials June 18, 2001.
     ICoS-3 Workshop: June 19-20, 2001.
     IJCAR: June 18-23, 2001


The invited speakers at ICoS-3 are:

     David Israel (SRI International)

     Alexander Koller (Saarbruecken)

     Ian Pratt-Hartmann (Manchester)


We will start off the workshop with two tutorials on June 18. This
gives the researchers from automated reasoning and computational
semantics respectively to get an understanding of the other field
before the actual workshop. The tutorials will given by

     Claire Gardent (CNRS, Nancy): Computational Semantics
                                   for automated reasoners

     Uli Furbach    (Univ. Koblenz):  Automated Reasoning
                                      for computational semanticists


The program committee for ICoS-3 consists of the following people:

     Patrick Blackburn, INRIA Lorraine (co-chair)
     Michael Kohlhase, Carnegie-Mellon University (co-chair)

     Johan Bos, Edinburgh
     Peter Baumgartner, Koblenz
     David Beaver, Stanford
     Dick Crouch, Xerox Parc
     Maarten de Rijke, Amsterdam
     Nissim Francez, Haifa
     Udo Hahn, Freiburg
     Gerard Huet, INRIA Rocquencourt
     Dale Miller, State College
     Martha Palmer, UPenn
     Stephen Pulman, Oxford
     Matthew Stone, Rutgers Univ
     Jun-ichi Tsuji, Tokyo
     Bonnie Webber, Edinburgh


We invite three kinds of submissions
(LaTeX2e, 11pt, one column, a4paper (not a4wide.sty)):

 - research papers on inference methods in computational semantics as well
   as their applications (15 pages),
 - system descriptions (6 pages), System descriptions should focus on
   actual implementations, explaining system architecture issues and
   specific implementation techniques. Every system description should be
   accompanied by a system demo at ICoS-3.
 - system demos (2 page abstracts): People who would like demonstrate
   systems that address inference in computational semantics should send
   two-page abstracts.

Research papers and system descriptions will be peer-refereed by the
programme committee above, system demos are only screened for
appropriateness by the program chairs.


NOTIFICATION: April 15, 2001.

The primary means of submission will be electronic, in PostScript
format. Submissions should be sent to the organizers.icos3 at

In addition to the (informal) workshop proceedings, we plan to publish
a special issue of the Journal of Language and Computation devoted to
ICoS-3. Shortly after the workshop, authors will be contacted by the
editors for special issue, inviting them to contribute; we may ask you
to incorporate comments/discussions/... arising during ICoS-3 into
your paper. Details on the publication schedule for the special issue
as well as formatting instructions will be announced at the workshop.
Registration and Further Information If you have any questions, please
contact the local organizers at icos3 at

If you have any questions, please contact the local organizers
Patrick Blackburn and Michael Kohlhase via icos3 at

For actual information concerning ICoS-3 please consult

Message diffusé par la liste Langage Naturel <LN at>
Informations, abonnement :
English version          :
Archives                 :

More information about the Ln mailing list