Several experiments have been carried out in the last 15 years investigating the use of various resources and techniques (e.g., thesauri, synonyms, word sense disambiguation, etc.) to help refine or enhance queries. However, the conclusions drawn on the basis of these experiments vary widely. Results of some studies have led to the conclusion that semantic information serves no purpose and even degrades results, while others have concluded that the use of semantic information drawn from external resources significantly increases the performance of retrieval software. At this point, several question arise:
These questions are fundamental not only to research in document retrieval, but also for information searching, question answering, filtering, etc. Their importance is even more acute for multilingual applications, where, for instance, the question of whether to disambiguate before translating is fundamental.
The goal of this workshop is to bring together researchers in the domain of document retrieval, and in particular, researchers on both sides of the question of the utility of enhancing queries with semantic information gleaned from languages resources and processes.
The workshop will provide a forum for presentation of the different points of view, followed by a roundtable in which the participants will assess the state of the art, consider the results of past and on-going work and the possible reasons for the considerable differences in their conclusions. Ultimately, they will attempt to identify future directions for research.
In view of the relevance of Word Sense Disambiguation (WSD) to information retrieval, a part of the workshop will be dedicated to a panel on Senseval and WSD evaluation[ http://www.itri.bton.ac.uk/events/senseval/]. The purpose of the panel is to open the discussion on the objectives and principles of Senseval-3, the next evaluation exercise for WSD systems.
The panel will summarize the methodology and results of Senseval-2 and consider the current state of WSD. Panelists will speak about the following topics: Is the Senseval-2 method of evaluation adequate? Are we building the right kind of lexical resources for real sense disambiguation systems? Should we (and is it possible to) start an application-specific evaluation track?
| Paper submission deadline | 15th February 2002 |
| Notification of acceptance | 15th March 2002 |
| Camera ready papers due | 8th April 2002 |
| Workshop | 2nd June 2002 |
Papers are requested that deal with one or more of the following topics (this is not an exhaustive list), and which make use of semantics applied to automatic information management:
Papers should not exceed 7 pages.
Submission must be sent by ELECTRONIC mail to loupy@sinequa.com. Please
write "LREC2002 workshop paper submission" in the subject line.
Accepted formats: Postscript (strongly preferred), PDF or RTF. No information about author(s) should appear in the submission paper.
Please send the following information in a separate file: the title to be printed in the programme of the Workshop; names and affiliations of the authors; the full address of the first author (or a contact person), including phone, fax, email, URL.
Formatting guidelines are provided at http://www.langnat.com/usirf.
The format described here may be modified for the final version.
Submissions must be received no later than 15th February 2002.
| Marc El-Bčze | Université d'Avignon et des Pays de Vaucluse (France) |
| Christian Fluhr | CEA (France) |
| Julio Gonzalo | Universidad Nacional de Educación a Distancia (Spain) |
| Graeme Hirst | University of Toronto (Canada) |
| Nancy Ide | Vassar College (USA) |
| Adam Kilgarriff | University of Brighton (UK) |
| Claude de Loupy | Sinequa (France) |
| Christian Marest | Mediapps (France) |
| Patrick Paroubek | LIMSI (France) |
| Piek Vossen | Irion Technologies (The Netherlands) |
| Phil Edmonds | Sharp Laboratories of Europe LTD (UK) |