There are now many computer programs for automatically determining the sense of a word in context (Word Sense Disambiguation or WSD). The purpose of SENSEVAL is to evaluate the strengths and weaknesses of such programs with respect to different words, different varieties of language, and different languages.
The first SENSEVAL took place in the summer of 1998 for English, French, and Italian, culminating in a workshop held at Herstmonceux Castle, Sussex, England on September 2-4.
SENSEVAL-2 is now underway. Directions for participating in the evaluation with your own WSD system are given below. The purpose of the workshop is to examine the results of the competition, to discuss the state-of-the-art in sense-tagging, to explore the implications of WSD evaluation, and to suggest directions for the future of SENSEVAL. July 5 will be closed to the public -- only participants of the competition will be permitted. July 6 will be open to all. Registration information will follow in due course.
SENSEVAL-2 will evaluate word sense disambiguation systems (or sense-tagging systems) on two types of task over 13 languages. In the "all-words" task, the evaluation is on almost all of the content words in a sample of texts. In the "lexical sample" task, first, we sample the lexicon, then we find instances in context of the sample words and the evaluation is on those instances only. (SENSEVAL-1 was exclusively a lexical-sample task.) The tasks are:
All-words task |
Lexical sample task |
Czech | Bangla |
Dutch | Basque |
English | Chinese |
Estonian | Danish |
English | |
Italian | |
Japanese | |
Korean | |
Spanish | |
Swedish |
Scott Cotton, University of
Pennsylvania
Phil Edmonds, Sharp Laboratories of Europe
Adam Kilgarriff, ITRI, University of Brighton
Martha Palmer, University of Pennsylvania
Email: senseval-coord@sharp.co.uk
Mailing list:
senseval-discuss@sharp.co.uk
(to join/leave send email to phil@sharp.co.uk)
SENSEVAL-2 Website: http://www.sle.sharp.co.uk /senseval2
last updated: 21 February, 2001 19:33 -0000