[Elsnet-list] ACL 2005 Workshop on Deep Lexical Acquisition

Anna Korhonen alk23 at cam.ac.uk
Thu Mar 3 16:53:00 CET 2005


     Sponsored by the ACL Special Interest Group on the Lexicon (SIGLEX)

                                30 June, 2005

                                Ann Arbor, USA


                     Submission deadline: 11 April, 2005


In natural language processing (NLP), there is a pressing need to develop 
deep lexical resources (e.g. lexicons for linguistically-precise grammars, 
template sets for information extraction systems, ontologies for word sense 
disambiguation). Such resources are critical for enhancing the performance 
of systems and for improving their portability between domains. For 
example, to perform reliably, an information extraction system needs access 
to high-quality lexicons or templates specific to the task at hand.

Most deep lexical resources have been developed manually by lexicographers. 
Manual work is costly and the resulting resources have limited coverage, 
and require labour-intensive porting to new tasks. Automatic lexical 
acquisition is a more promising and cost-effective approach to take, and is 
increasingly viable given recent advances in NLP and machine learning 
technology, and corpus availability.

While advances have recently been made in some areas of automatic deep 
lexical acquisition, a number of important challenges need addressing 
before benefits can be reaped in practical language engineering:

  * Acquisition of deep lexical information from corpora

  While corpus data has been successfully applied in learning certain types 
  deep lexical information (e.g. semantic relations, subcategorization,
  selectional preferences), there remain a broad range of lexical relations
  that corpus-based techniques have yet to be applied to.

  * Accurate, large-scale, portable acquisition techniques

  One of the biggest current research challenges is how to improve the
  accuracy of existing acquisition techniques further, at the same time as
  improving both scalability and robustness.

  * Use of deep lexical acquisition in recognised applications

  Although lexical acquisition has the potential to boost performance in 
  NLP application tasks, this has yet to be demonstrated for many important

  * Multilingual deep lexical acquisition

  For theoretical and practical reasons it is important to test whether
  techniques developed for one language (typically English) can be used to
  benefit research on other languages.


The workshop will be of interest to anyone interested in automatically
acquired deep lexical information, e.g. in the areas of computational
grammars, computational lexicography, machine translation, information
retrieval, question-answering, and text mining.  Areas of Interest

  * Automatic acquisition of deep lexical information:
    o subcategorization
    o diathesis alternations
    o selectional preferences
    o lexical / semantic classes
    o qualia structure
    o lexical ontologies
    o semantic roles
    o word senses

  * Methods for supervised, unsupervised and weakly supervised deep lexical
    acquisition (machine learning, statistical, example- or rule-based, 

  * Large-scale, cross-domain, domain-specific and portable deep lexical

  * Extending and refining existing lexical resources with automatically
    acquired information

  * Evaluation of deep lexical acquisition

  * Application of deep lexical acquisition to NLP applications (e.g. 
    translation, information extraction, language generation,

  * Multilingual deep lexical acquisition


Paper submission deadline: 11 April, 2005

Notification date: 2 May, 2005

Camera-ready submission deadline: 16 May, 2005

Workshop date: 30 June, 2005



Papers should describe original work; they should emphasize completed work 
rather than intended work, and should indicate clearly the state of 
completion of the reported results. Wherever appropriate, concrete 
evaluation results should be included. Submissions will be judged on 
correctness, originality, technical strength, significance and relevance to 
the conference, and interest to the attendees.

A paper accepted for presentation at the 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 or 
workshops must indicate this on the title page, as must papers that contain 
significant overlap with previously published work. Reviewing

The reviewing of the papers will be blind. Each submission will be reviewed 
by at least three programme committee members. Submission Information

Submissions should follow the two-column format of ACL proceedings and 
should not exceed eight (8) pages, including references. We strongly 
recommend the use of ACL-05 LaTeX style files or Microsoft Word Style 
files. They are available at http://www.aclweb.org/acl2005/styles/. A 
description of the format is also available in case you are unable to use 
these style files directly. Papers must conform to the official ACL-05 
style guidelines, and we reserve the right to reject submissions that do 
not conform to these styles including font size restrictions.

As reviewing will be blind, the paper should not include the authors' names 
and affiliations. Furthermore, self-references that reveal the author's 
identity, e.g., "We previously showed (Smith, 1991) ...", should be 
avoided. Instead, use citations such as "Smith previously showed (Smith, 
1991) ...". Papers that do not conform to these requirements will be 
rejected without review.

Papers should be submitted electronically in BOTH Postscript and PDF format
to: dla-acl2005 at unimelb.edu.au

The following identification information should be sent in a separate email
with the subject line "ACL2005 WORKSHOP ID PAGE":

    Title: title of paper 
    Authors: list of all authors 
    Keywords: up to five topic keywords 
    Contact author: email address of author of record (for correspondence) 
    Abstract: abstract of paper (not more than 10 lines) 

Notification of receipt will be emailed to the contact author.


  Timothy Baldwin 
  University of Melbourne, Australia

  Anna Korhonen 
  University of Cambridge, UK 
  NII, Japan

  Aline Villavicencio 
  University of Essex, UK


  Collin Baker (University of California Berkeley, USA) 
  Roberto Basili (University of Rome Tor Vergata, Italy) 
  Francis Bond (NTT, Japan) 
  Chris Brew (Ohio State University, USA) 
  Ted Briscoe (University of Cambridge, UK) 
  John Carroll (University of Sussex, UK) 
  Stephen Clark (University of Oxford, UK) 
  Sonja Eisenbeiss (University of Essex, UK) 
  Christiane Fellbaum (University of Princeton, USA) 
  Frederick Fouvry (University of Saarland, Germany) 
  Sadao Kurohashi (University of Tokyo, Japan) 
  Diana McCarthy (University of Sussex, UK) 
  Rada Mihalcea (University of North Texas, USA) 
  Tom O'Hara (University of Maryland, Baltimore County, USA) 
  Martha Palmer (University of Pennsylvania, USA) 
  Massimo Poesio (University of Essex, UK) 
  Philip Resnik (University of Maryland, USA) 
  Patrick Saint-Dizier (IRIT-CNRS, France) 
  Sabine Schulte im Walde (University of Saarland, Germany) 
  Mark Steedman (University of Edinburgh, Scotland, UK) 
  Mark Stevenson (University of Sheffield, UK) 
  Suzanne Stevenson (University of Toronto, Canada) 
  Dominic Widdows (MAYA Design, Inc., USA) 
  Yorick Wilks (University of Sheffield, UK) 
  Dekai Wu (Hong Kong University of Science and Technology) 

More information about the Elsnet-list mailing list