|
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.
Workshop programme
| 8:30 | Welcome |
| 8:40 | Roger
Evans: What use is a corpus for NLG? (introductory presentation) |
| 9:00 | Irene
Langkilde-Geary: Constraint programming as a Whiteboard Architecture
for Probabilistic NLG |
| 10:00 | Nikiforos Karamanis & Chris Mellish: A Review of Recent
Corpus-based Methods for Evaluating Text Structuring in Natural
Language Generation |
| 10:30 | Break |
| 11:00 | Sandra Williams & Ehud Reiter: Deriving content
selection rules from a corpus of non-naturally occurring documents for
a novel NLG application |
| Tomasz Marciniak & Michael
Strube: Using an Annotated Corpus as a Knowledge Source for
Language Generation |
| Huayan Zhong & Amanda
Stent: Building Surface Realizers Automatically From Corpora
Using General-Purpose Tools |
| 12:30 | Lunch |
| 1:30 | Amy
Isard, Carsten Brockmann & Jon Oberlander: Re-Creating Dialogues from a
Corpus |
| Stephen Wan:
Statistically Generated Summary Sentences: A Preliminary Evaluation
of Verisimilitude using Precision of Dependency Relations |
| Surabhi Gupta & Amanda
Stent: Automatic Evaluation of Referring Expression Generation
Using Corpora |
| 3:00 | Break |
| 3:30 | Rashmi Prasad, Aravind Joshi, Nikhil Dinesh, Alan Lee,
Eleni Miltsakaki & Bonnie Webber: The Penn Discourse TreeBank
as a Resource for Natural Language Generation |
| Short corpus presentations: |
| Ehud Reiter: Memories
For Life (M4L) Corpus
Bayan Abu Shawar & Eric Atwell: Re-Creating Dialogues from Corpora
|
| 4:30 | Panel on Exploiting Corpora for NLG |
Key workshop facts
Invited speaker:
Irene Langkilde-Geary, Brigham Young University, USA
Panel on Statistical Generation:
Chris Brew, Linguistics, Ohio State University, USA
Irene Langkilde-Geary, Brigham Young University, USA
Ehud Reiter, Computing Science, University of Aberdeen, UK
Bonnie Webber, Informatics, University of Edinburgh, UK
Programme committee:
Anja Belz, ITRI, University of Brighton, UK
John Carroll, Informatics, University of Sussex, UK
Robert Dale, Macquarie University, Australia
Michel Gﯩreux, ITRI, University of Brighton, UK
Kevin Knight, ISI, University of Southern California, USA
Chris Mellish, University of Aberdeen, UK
Stephan Oepen, Oslo University, Norway, and CSLI Stanford, USA
Sebastian Varges, CSLI, Stanford University, USA
Registration
Registration is open at the Corpus Linguistics 2005
website. Please note that Using Corpora for NLG is a full-day
workshop, and that you do not need to register for the main
conference. Simply select the appropriate options in the registration
form. The workshop registration fee is 70 Pounds.
Camera-ready instructions
The final paper should be up to six pages long. It may be up to 8
pages long if you require extra space for long bibliographies,
graphical illustrations, sample system output, algorithm details or
similar matter. Please do take into account the reviewers' comments
wherever possible.
Please follow the IJCAI
formatting instructions and use the supplied Word
templates or Latex
sources.
Papers must be submitted in pdf format, with no page numbers.
Camera-ready papers should be sent by email to . The deadline is 1st July.
We look forward to seeing you in Birmingham on 14th July.
|
|
|
