MT Summit VIII

Workshop on MT Evaluation

  

Proceedings of the Workshop

21 September 2001, Santiago de Compostela, Spain

(Organisers: Eduard Hovy, Margaret King, Sandra Manzi, and Florence Reeder)

Contents

Programme of papers

 

- Session 1: The ISLE taxonomy for MT Evaluation and its use

Andrei Popescu-Belis, Sandra Manzi & Maghi King: Towards a two-stage taxonomy for machine translation evaluation [PDF, 187KB]

Elia Yuste-Rodrigo & Francine Braun-Chen: Comparative evaluation of the linguistic output of MT systems for translation and information purposes [PDF, 134KB]

Keith J. Miller, Donna M. Gates, Nancy Underwood & Josemina Magdalen: Evaluating machine translation output for an unknown source language: report of an ISLE-based investigation [PDF, 99KB]

Michelle Vanni & Keith J. Miller: Scaling the ISLE framework: validating tests of machine translation quality for multi-dimensional measurement [PDF, 121KB]

 

- Session 2: Correlations between evaluation measures

Martin Rajman & Tony Hartley: Automatically predicting MT systems rankings compatible with fluency, adequacy and informativeness scores [PDF, 154KB]

John White: Predicting intelligibility from fidelity in MT evaluation [PDF, 235KB]

 

- Session 3: Analytic measures of output quality, focusing on noun phrases

Palmira Marrafa & António Ribeiro: Quantitative evaluation of machine translation systems: sentence level [PDF, 65KB]

John White & Monika Forner: Predicting MT fidelity from noun-compound handling [PDF, 64KB]

Widad Mustafa El Hadi, Ismail Timimi & Marianne Dabbadie: Setting a methodology for machine translation evaluation [PDF, 99KB]

Florence Reeder, Keith Miller, Jennifer Doyon & John White: The naming of things and the confusion of tongues: an MT metric [PDF, 80KB]

 

- Session 4: MT Evaluation in relation to other domains

Christine Bruckner & Mirko Plitt: Evaluating the operational benefit of using machine translation output as translation memory input [PDF, 32KB]

Florence Reeder: In one hundred words or less [PDF, 80KB]