CESTA - Campagne d’Evaluation de Systèmes de Traduction Automatique (Evaluation of MT systems)

Presentation

The CESTA campaign proposes a series of evaluation campaigns of machine translation systems for various language pairs towards French. The statistical metrics BLEU/NIST (IBM) are being used for the evaluations and adapted to French as a target language, along with other automatic metrics based on grammatical and semantic scores (X-Score and D-Score). The Weighted N-gram Model (WNM), WER and PER are also used. The other aim of CESTA is to conduct a meta-evaluation, comparing the automatic results with human judgments.

Coordinator

  ELDA

Participants

  Université de Lille 3, IDIS/CESARTES
  Ecole Polytechnique Fédérale de Lausanne, LIA
  Université de Leeds
  Temis S.A.
  Systran S.A.
  Softissimo S.A.
  CIMOS S.A.
  Université de Grenoble, IMAG
  Université de Montréal, Dept. Linguistique et Traduction
  Université de Montréal, RALI
  Université de Genève, ISSCO
  University of Aachen, RWTH
  Universitat Politècnica de Catalunya (UPC)
  SDL International
  Comprendium S.L.

Contact :

  Olivier Hamon

For more information (in French), please visit Technolangue.Net.