The FEMTI guidelines for contextual MT evaluation: principles and resources

Authors

  • Paula Estrella FaMAF, National University of Córdoba, Argentina
  • Andrei Popescu-Belis Idiap Research Institute, Martigny, Switzerland
  • Maghi King ISSCO/TIM/ETI, University of Geneva, Switzerland

DOI:

https://doi.org/10.52034/lanstts.v8i.244

Keywords:

MT evaluation, contextual evaluation, quality models for MT, contexts of use for MT, evaluation plans, web-based interfaces, FEMTI

Abstract

A large number of evaluation metrics exist for machine translation (MT) systems, but depending on the intended context of use of such a system, not all metrics are equally relevant. Based on the ISO/IEC 9126 and 14598 standards for software evaluation, the Framework for the Evaluation of Machine Translation in ISLE (FEMTI) provides guidelines for the selection of quality characteristics to be evaluated depending on the expected task, users, and input characteristics of an MT system. This approach to contextual evaluation was implemented as a web-based application which helps its users design evaluation plans. In addition, FEMTI offers experts in evaluation the possibility to enter and share their knowledge using a dedicated web-based tool, tested in several evaluation exercises.

Downloads

Published

25-10-2021

How to Cite

Estrella, P., Popescu-Belis, A., & King, M. (2021). The FEMTI guidelines for contextual MT evaluation: principles and resources. Linguistica Antverpiensia, New Series – Themes in Translation Studies, 8. https://doi.org/10.52034/lanstts.v8i.244