[Corpora-List] CL05 Workshop on Using Corpora for NLG - Second Call for Papers

Anja Belz a.s.belz at itri.brighton.ac.uk
Tue May 17 16:31:00 CEST 2005

Using Corpora for Natural Language Generation - Second Call for Papers

Using Corpora for Natural Language Generation is a pre-conference
workshop at Corpus Linguistics 2005, to be held in Birmingham, 14
July 2005.

We aim to bring together researchers who use corpora for NLG research
either in the traditional, manual way, or automatically, involving
machine learning and statistical methods. The goal of the workshop is
to present and discuss current research, to compare manual and
automatic corpus exploitation, to evaluate achievements, and to
identify challenges for the future.

We invite the submission of papers on original and unpublished
research on all aspects of using corpora for natural language
generation, including, but not limited to:

* (Partial) automation of traditional corpus analysis for NLG
* Issues in annotating corpora for NLG
* Statistical approaches to deep and/or surface generation
* Machine learning methods for deep and/or surface generation
* Role of corpora in the evaluation of NLG systems
* Reuse of resources developed for NLU (e.g. treebanks) in NLG
* Domain-specific vs. general purpose corpora for NLG

We would like to emphasise that where we say `NLG' we mean to include
the language generation components of MT and dialogue systems.

Invited Speaker

Irene Langkilde-Geary (Brigham Young University, Provo, USA) will give
an invited talk with the provisional title: Constraint programming
as a Whiteboard Architecture for Probabilistic NLG.

Panel on Exploiting Corpora for NLG

We will hold a panel discussion on the topics of this workshop.
The following researchers have agreed to join the panel:

Irene Langkilde-Geary, Computer Science, Brigham Young University, USA
Donia Scott, Computing Research Centre, The Open University, UK
Bonnie Webber, Informatics, University of Edinburgh, UK
Ehud Reiter, Computing Science, University of Aberdeen, UK
Chris Brew, Linguistics, Ohio State University, USA


The proceedings of the workshop will be published in printed form and
electronically on the web. We plan to publish selected papers in a
special issue of a suitable journal.


Papers should describe original work, emphasizing actual rather than
intended work, and should indicate clearly the state of completion of
the reported results. Wherever appropriate, concrete evaluation of
results should be included. A paper submitted to the Workshop on Using
Corpora for NLG cannot have previously been published. Papers that are
being submitted to other conferences or workshops should indicate

Submission information

Reviewing will be based on abstracts, the final proceedings will
contain papers of 4-6 pages.

* Submission of abstracts:

Submissions should be extended abstracts of papers, and should be sent
in PDF format by email to ucnlg at itri.brighton.ac.uk. Abstracts should
not exceed 500 words. RTF format is also accepted but not encouraged.

Reviewing of papers will be blind. Reviewing will be managed by the
workshop's international programme committee. Final decisions on the
technical programme will be made by the workshop organisers.

As reviewing will be blind, the paper should not include the authors'
names and affiliations. Self-references that reveal the authors'
identity, e.g., "We previously showed (Smith, 1991) ...", should be
avoided. Instead, use citations such as "Smith previously showed
(Smith, 1991) ...".

In the body of the email submitting the abstract, please include
the authors' names and affiliations, and the paper title.

* Camera-ready full-length papers:

4-6 pages in the IJCAI'05 format. Please follow the IJCAI formatting
instructions (http://ijcai05.csd.abdn.ac.uk/). Further submission
instructions for full-length papers will be included in acceptance

Important dates

Abstract submission deadline: Friday 27th May 2005
Notification of acceptance: Friday 10th June 2005
Camera-ready full-length papers: Friday 1st July 2005
Date of workshop: Thursday 14th July

Programme committee

Anja Belz, ITRI, University of Brighton, UK
John Carroll, Informatics, University of Sussex, UK
Robert Dale, Centre for Language Technology, Macquarie University, Australia
Michel Genereux, ITRI, University of Brighton, UK
Kevin Knight, ISI, University of Southern California, USA
Chris Mellish, Computing Science, University of Aberdeen, UK
Sebastian Varges, ITRI, University of Brighton, UK

Workshop website


More information about the Corpora-archive mailing list