SENSEVAL workshop programme 
Herstmonceux Castle, Sussex, England 
2- 4 September 1998

(as at 24 Aug)

Tuesday 1st

arrivals, dinner (8.00pm)

Wednesday 2nd

 
AM  The evaluation framework 
9.30  Welcome, framework for English SENSEVAL: Adam Kilgarriff
9.50  ROMANSEVAL framework for French and Italian: Jean Veronis
10.10  Inter-tagger agreement for: 
French (10 mins, Jean Veronis)
Italian (10 mins, Nicoletta Calzolari
English (20 mins, Adam Kilgarriff
11.00  TEA/COFFEE 
11.30  Lexicographer's experience of tagging: Ramesh Krishnamurthy and Diane Nicholls 
12.00  Results for: 
French (15 mins, Jean Veronis
Italian (10 mins, Nicoletta Calzolari
English (30 mins, Joseph Rosenzweig
1.00 LUNCH 
PM  Participating systems 
(24 participating systems for English, French or Italian) 
2.30  10 x 5 mins presentations + half-hour discussion 
4.00  TEA/COFFEE 
4.30  Debate: "Computational criteria for consistent sense distinctions" 
Chair: Martha Palmer 
Panelists: Nancy Ide, David Yarowsky, Rosamund Moon 
7.30  RECEPTION / BUFFET 
 

Thursday 3rd:

AM  Participating systems (cont.) 
9.30  Report on ARCADE (evaluation for text alignment): Jean Veronis 
9.50  8 x 5 mins presentations + half-hour discussion 
11.00  TEA/COFFEE 
11.30  7 x 5 mins presentations 
12.10  Plenary discussion: what worked well, where and how? 
1.00  LUNCH 
PM  There will be a meeting of the ARCADE project, for details see: http://www.lpl.univ-aix.fr/projects/arcade/ 
Other options include: 
* cycling, walking etc in vicinity of Herstmonceux (including Roman ruins of Pevensey castle) 
* trip into Brighton to sample delights of UK's foremost seaside resort! 
 

Friday 4th:

AM  Pressing Issues 
9.30  Is Word Sense Tagging just one more task, or is it special? Yorick Wilks
9.50  More than one sense per discourse: Bob Krovetz
10.10  Topics listed below form a preliminary list: suggestions for additions and other changes are welcome. We are canvassing levels of interest to work out what should be plenary, what should be in parallel etc. Feedback please! 
* What lexical resources/sense inventories to use
* Selection of corpus data
* Word selection; lexical-sample and all-words tasks
* Interaction with POS-tagging
* Scoring
* What sorts of lexical representations were used by participating systems: implications for, e.g., EAGLES working group on lexical semantics standards 
* Tools for manual sense-tagging
* SENSEVALs for further languages
* Mapping senses between dictionaries 
1.00  LUNCH 
PM  The way ahead 
2.30  Invited Speaker: Patrick Paroubek, ELSE (Evaluation in Language and Speech Engineering) ELSE and future SENSEVALs
3.00  * Should there be a next SENSEVAL, and if so, when, where and how (to include: who should bid for funding, and from whom) 
* Was the pilot SENSEVAL model a good one? Which tasks did it miss out, which systmes did it unfairly disadvantage? 
4.00  TEA, DEPARTURES 
 

This page is maintained by Carole Tiberius and was last modified on 14 July 1998.


| SENSEVAL home page | Registration |