14.411, Calls: Paraphrase/Natural Lang Learning

LINGUIST List linguist at linguistlist.org
Tue Feb 11 18:02:06 UTC 2003

LINGUIST List:  Vol-14-411. Tue Feb 11 2003. ISSN: 1068-4875.

Subject: 14.411, Calls: Paraphrase/Natural Lang Learning

Moderators: Anthony Aristar, Wayne State U.<aristar at linguistlist.org>
            Helen Dry, Eastern Michigan U. <hdry at linguistlist.org>

Reviews (reviews at linguistlist.org):
	Simin Karimi, U. of Arizona
	Terence Langendoen, U. of Arizona

Home Page:  http://linguistlist.org/

The LINGUIST List is funded by Eastern Michigan University, Wayne
State University, and donations from subscribers and publishers.

Editor for this issue: Karolina Owczarzak <karolina at linguistlist.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


Date:  Mon, 10 Feb 2003 11:34:30 EST
From:  Priscilla Rasmussen <rasmusse at cs.rutgers.edu>
Subject:  Paraphrase Acquisition and Applications, Japan

Date:  Mon, 10 Feb 2003 11:44:19 EST
From:  Priscilla Rasmussen <rasmusse at cs.rutgers.edu>
Subject:  Natural Language Learning, Japan

-------------------------------- Message 1 -------------------------------

Date:  Mon, 10 Feb 2003 11:34:30 EST
From:  Priscilla Rasmussen <rasmusse at cs.rutgers.edu>
Subject:  Paraphrase Acquisition and Applications, Japan



Second International Workshop on Paraphrasing:
    Paraphrase Acquisition and Applications

    July 11, 2003, in Sapporo, Japan
    in conjunction with ACL-2003 (WS5)


A common characteristic of human languages is the possibility to
convey the same information in several ways. Paraphrases, which in the
literature have also been referred to as variants, reformulations, or
inference rules, span a wide range of variation:

- article / paper / publication
- Oswald killed Kennedy. / Kennedy was assassinated by Oswald.
- a plant in Alabama / the Alabama plant
- Edison invented the light bulb. / Edison's invention of the light bulb
- He plays better than everybody else in the team. / He's the best in the team.
- The tree healed its wounds by growing new bark. / The tree healed
its wounds. It grew new bark.
- The stapler costs $10. / The price of the stapler is $10.
- Where is Thimphu located? / Thimphu is the capital of what country?

This diversity of expression presents a major challenge for many NLP
applications. Thus, automatic paraphrase identification and generation
can benefit a broad range of NLP tasks, including machine translation,
summarization, information retrieval, question answering, generation,
and authoring and reading assistance.

Previous workshops on paraphrasing:
  - Workshop on Automatic Paraphrasing, November 2001
      accompanying the NLPRS2001 conference, with 55 participants
  - Workshop on Automatic Paraphrasing (in Japanese), March 2001
      accompanying Japanese NLP conference, with 165 participants


The workshop will be open to any research topic related to
paraphrases.  More specifically, topics of interest include, but are
not limited to:

* definition and typology of paraphrases
* representation of paraphrases
* algorithms for recognizing, generating and choosing among paraphrases
* construction of paraphrase resources
* existing and potential applications of paraphrases:
- question answering, summarization, information retrieval,
      machine translation, authoring and reading assistance
- inferencing with paraphrases
* evaluation of paraphrase algorithms and resources

Special topic: Paraphrase Acquisition

The increased availability of parallel corpora and comparable corpora
has opened up possibilities for automatic paraphrase acquisition.  As
we have recently witnessed, a number of new methods for paraphrase
extraction have emerged.

The availability of appropriate evaluation techniques is a key part of
a progress in the area.  Is it possible to create a common benchmark
for evaluating different paraphrase extraction approaches?  On which
terms should different acquisition approaches be compared? How can we
define the notion of baseline?

Another important objective of the workshop is to take a first step
towards a standardized paraphrase resource that could be shared among
a large variety of researchers.

  :is-equivalent-to "the price of SOMETHING_1 is MONETARY_QUANTITY_2"
  :can-be-inferred-from "to sell SOMETHING_1 for MONETARY_QUANTITY_2"

Such a resource, with possibly tens of thousands of entries such as
the one above (in one format or another), can be viewed as a valuable
extension of WordNet and holds great promise to advance many areas of
natural language processing.


Paper submissions must be anonymous and are limited to at most 8 pages
including references, figures etc.  Authors are encouraged (but not
required) to use the ACL style format of the main conference. Only
electronic submissions will be accepted. Please email your submission
in pdf (preferred), postscript, or MS Word to the following address:

  iwp2003-submission at nlp.nagaokaut.ac.jp

Each submission should also specify the author's name, affiliation,
postal address, email address and title in the body of the email
message.  For more information, please make contact with the workshop

  Kentaro Inui, NAIST: inui at is.aist-nara.ac.jp
  Ulf Hermjakob, ISI:  ulf at isi.edu


Paper submission deadline:    April 21, 2003
Notification of acceptance:   May 14, 2003
Camera-ready manuscripts due: May 26, 2003
Workshop date:                July 11, 2003


  Kentaro Inui, Co-Chair, Nara Institute of Science and Technology, Japan
  Ulf Hermjakob, Co-Chair, USC Information Sciences Institute, USA
  Regina Barzilay, Cornell University, USA
  Mark Dras, Macquarie University, Australia
  Satoshi Sato, Kyoto University, Japan
  Kazuhide Yamamoto, Nagaoka Univ. of Tech./ATR, Japan


  Bruce Croft, University of Massachusetts, USA
  Sanda Harabagiu, University of Texas at Dallas, USA
  Graeme Hirst, University of Toronto, Canada
  Christian Jacquemin, LIMSI, France
  Hongyan Jing, IBM T.J. Watson Research Center, USA
  Gen'ichiro Kikui, ATR, Japan
  Judith Klavans, Columbia University, USA
  Helen Langone, Princeton (WordNet team), USA
  Maria Lapata, University of Edinburgh, UK
  Dekang Lin, University of Alberta, Canada
  Daniel Marcu, USC Information Sciences Institute, USA
  Teruko Mitamura, Carnegie Mellon University, USA
  Hiroshi Nakagawa, Tokyo University, Japan
  Patrick Pantel, University of Alberta, Edmonton, Canada
  Harold Somers, Univ. of Manchester Institute of Science and Technology, UK
  Karen Sparck-Jones, University of Cambridge, UK
  Manfred Stede, Universitaet Potsdam, Germany
  Ralph Weischedel, BBN, USA
  Yujie Zhang, CRL, Japan
  Chengqing Zong, Chinese Academy of Sciences, PRC
  Ingrid Zukerman, Monash University, Australia

-------------------------------- Message 2 -------------------------------

Date:  Mon, 10 Feb 2003 11:44:19 EST
From:  Priscilla Rasmussen <rasmusse at cs.rutgers.edu>
Subject:  Natural Language Learning, Japan


     CoNLL-2003: Seventh Conference on Natural Language Learning

	     Organized at HLT-NAACL-02, Edmonton, Canada

			 May 31 - June 1 2003


CoNLL is an international forum for discussion and presentation of
research on natural language learning. We invite submission of papers
about natural language learning topics, including, but not limited to:

     - Computational models of human language acquisition
     - Computational models of the origins and evolution of language
     - Machine learning methods applied to natural language processing
       tasks (speech processing, phonology, morphology, syntax,
       semantics, discourse processing, language engineering
     - Symbolic learning methods (Rule Induction and Decision Tree
       Learning, Lazy Learning, Inductive Logic Programming, Analytical
       Learning, Transformation-based Error-driven Learning)
     - Biologically-inspired methods (Neural Networks, Evolutionary
     - Statistical methods (Bayesian Learning, HMM, maximum entropy,
       SNoW, Support Vector Machines)
     - Reinforcement Learning
     - Active learning, ensemble methods, meta-learning
     - Computational Learning Theory analysis of language learning
     - Empirical and theoretical comparisons of language learning methods
     - Models of induction and analogy in Linguistics

CoNLL is the yearly meeting organized by SIGNLL, the Association for
Computational Linguistics Special Interest Group on Natural Language
Learning. After previous CoNLL meetings were held in Madrid (1997),
Sydney (1998), Bergen (1999) Lisbon (2000), Toulouse (2001), and
Taipei (2002).

See http://www.aclweb.org/signll and

for more information about SIGNLL and CoNLL.

Special Theme
- -----------

As in previous years, in addition to submissions on the general topics
listed above, we encourage submissions on a special theme. This year's
special theme is:

       Semi-supervised / unsupervised learning and sample selection
       techniques for language learning (co-training, active learning,
       EM, etc).

Supervised Machine Learning methods suffer from a "data annotation
bottleneck" which is especially harmful for language learning tasks
where a lot of training data is needed (e.g. parsing). Sample
selection techniques, and combination of supervised learning with
semi-supervised and unsupervised techniques may provide a solution to
this problem.

Shared Task
- ---------

This year's workshop will also accept submissions for a shared task:
machine learning approaches to named entity recognition. Special
attention will be given to the use of multiple sources of knowledge,
like training data, lists of examples and unannotated data.
Interested groups will be supplied with the same training and testing
material (in several languages), and will all use the same evaluation
criteria, thus allowing comparison between various learning methods.

More information on the shared task will be available at:


Invited Speaker
- -------------


- ---------

* Main Session Submissions

Submit a full paper of no more than 8 pages (Postscript, PDF or plain
text ASCII) by March 16, 2003 electronically to the address below.
Authors of accepted submissions will be invited to produce a final
paper to be published in the proceedings of the workshop, which will
be available at the workshop for participants, and distributed
afterwards by ACL. Final submissions must follow the HLT-NAACL style
We strongly recommend the use of these style files also in the

Submit main session papers to:

Walter Daelemans
daelem at uia.ua.ac.be
CNTS Language Technology Group, University of Antwerp,
Universiteitsplein 1, B-2610 Antwerpen, Belgium.
Tel: +32 3 8202766; Fax: +32 3 8202662

* Shared Task Submissions

Submit a paper of maximum 4 pages describing the learning approach,
and your results on the test set by March 16, 2003 to the address
below (preferably by email). A special section of the proceedings will
be devoted to a comparison and analysis of the results and to a
description of the approaches used. Submit shared task submissions to:

Erik Tjong Kim Sang, erikt at uia.ua.ac.be or
Centrum Nederlandse Taal en Spraak
Linguistics, Department of Germanic languages and literature
UIA, University of Antwerp
Universiteitsplein 1, B-2610 Wilrijk, Belgium

Important Dates
- -------------

     Deadline for Paper Submission: March 16, 2003
     Deadline for Shared Task Submission: March 16, 2003
     Notification: March 24, 2003
     Deadline camera-ready paper: April 10, 2003
     Conference: May 31-June 1 2003

Programme Committee
- -----------------

Walter Daelemans (Belgium & The Netherlands), co-chair
Miles Osborne (UK), co-chair
Erik Tjong Kim Sang (Belgium), shared task chair
Dan Roth (USA)
Thorsten Brants (USA)
Claire Cardie (USA)
James Cussens (UK)
Diane Litman (USA)
Yuji Matsumoto (Japan)
Raymond Mooney (USA)
John Nerbonne (The Netherlands)
David Powers (Australia)
Adwait Ratnaparkhi (USA)
Antal van den Bosch (The Netherlands)
Rada Mihaelcea (USA)
Ted Pedersen (USA)

LINGUIST List: Vol-14-411

More information about the Linguist mailing list