Improving Contextual Quality Models for MT Evaluation Based on Evaluators' Feedback
The Framework for Machine Translation Evaluation (FEMTI), introduced by the ISLE Evaluation Working Group, contains guidelines for defining a quality model used to evaluate an MT system, in relation to the purpose and context of use of the system. In this paper, we report results from a recent experiment aimed at transferring knowledge from MT evaluation experts into the FEMTI guidelines, in particular, to populate relations denoting the influence of the context of use of a system on its evaluation. The results of this hands-on exercise carried out as part of a tutorial, are publicly available at http://www.issco.unige.ch/femti/.
Record created on 2010-02-11, modified on 2016-08-08