[Date Prev][Date Next][Thread Prev][Thread Next][Chronological Index][Thread Index]

Re: EAGLESEVAL: Questions to named individuals.

Hello Everybody!

here is a batch of questions from Granada that were specifically addressed
to particular individuals. That doesn't stop anyone else answering them

From Martin Rajman to Lin Chase:

Computing cross entropy is interesting, but is there any evidence showing
that it correlates with the accuracy of the systems?

From Martin Rajman to Marc Blasband:

Measuring and taking into account user satisfaction (i.e. adequacy of the
system with end users needs) is important, but not the most important
element in evaluation. It does not allow progress in the field ... it only
increases the return on investment.

From Christophe Jouis to Richard Sutcliffe:

Becasue we have the same problem in terminology evaluation, I would like to
ask a naive question. It is about criteria for evaluation:

a) What is a 'correct' analysis?

b) who is able to decide?

From Marc Blasband to Joseph Mariani:

Effort to involve end users in his programme?

Questions based on notes taken by the organisers.


Please note my new e-mail address (old address was king@divsun.unige.ch)
Maghi King                   | E-mail: Margaret.King@issco.unige.ch
ISSCO, University of Geneva  | WWW: http://issco-www.unige.ch/
54 route des Acacias         | Tel: +41/22/705 71 14
CH-1227 GENEVA (Switzerland) | Fax: +41/22/300 10 86