Sponsored by IBM
This workshop is part of a bi-annual series of workshops about natural language generation that runs since 1987. Previous European workshops have been held at Royaumont, Edinburgh, Judenstein, Pisa, Leiden, Duisburg, and Toulouse. The goal of the workshop is to be an informal meeting which facilitates the dissemination of knowledge and expertise in the field. The workshop will focus on the following topics:
There seems to be a substantial discrepancy between application-oriented systems and principled approaches to NLG. Accomodating a standard pipeline architecture with suitable heuristic preferences to the intended functionality of a system stands in contrast to several principled approaches to searching which have been tried out so far. These include blackboard architectures, constraint propagation and, more recently genetic algorithms and statistical techniques. A comparison of these methods in terms of their potential and limitations is likely to improve understanding about this issue. Gained insights could prove fruitful for building applications in a more general and, thus, better reusable way, especially in large-scale applications such as summarization and machine translation.
Whether the generation task is to verbally express contents of some knowledge base or to produce multi-lingual presentations from language-neutral or similar representations, there are strong similarities in building the target representations: In the overwhelming number of cases, the ordering and embedding of elements in the source representation is reflected by the ordering and embedding of their corresponding realizations at the surface. Often, this reflection is systematic, many times even simple. But a few cases prove complex and involve a major restructuring of the surface structure when compared to the source structure. A major emphasis of this topic is on collecting such complex cases, identifying commonalities between them and discussing restructuring techniques.
|Helmut Horacek||Univ. of the Saarland|
|Nicolas Nicolov||IBM T.J. Watson Research Center|
|Leo Wanner||Univ. of Stuttgart|
|John Bateman||Univ. of Bremen|
|Dan Cristea||Univ. of Iasi|
|Robert Dale||Macquarie University|
|Laurence Danlos||Universite Paris 7|
|Marc Dymetman||Xerox Research Centre Europe, Grenoble|
|Michael Elhadad||Ben-Gurion Univ.|
|Kristiina Jokinen||Univ. of Art and Design Helsinki|
|Richard Kittredge||Univ. of Montreal & CoGenTex|
|Chris Mellish||Univ. of Edinburgh|
|Sergei Nirenburg||CRL, New Mexico|
|Owen Rambow||AT&T Research|
|Ehud Reiter||Univ. of Aberdeen|
|Manfred Stede||Technical University of Berlin|
|Michael Zock||LIMSI, CNRS|
We also invite poster submissions (free format, up to 6 page, PDF).
The submissions should be associated with a cover email containing the following information (ASCII text):
# TITLE: <title of the paper> # AUTHORS: <list of authors> # EMAIL: <email of author for correspondence> # KEYWORDS: <keywords, topic sub-areas, ...> # ABSTRACT: <abstract of the paper>
|Paper submissions||*** 6 April 2001 ***|
|Notification of acceptance||27 April 2001|
|Camera-ready copies due||16 May 2001|
|Registration deadline||as ACL|
|Workshop dates||6-7 July 2001|
People wishing to attend the workshop but not submitting papers should send a notification of attendance: a 1-2 page stating interest to participate, work done in NLG so far, and potential contributions / material for discussions about one of the topics. This informationn will help with the organisation of discussions and allow for an informal and highly interactive character of the workshop. Notifications of attendance should be sent to Helmut Horacek (firstname.lastname@example.org).