MTEval Workshop
ISSCO, Geneva, 19-24 April 2001

"An Invitation to Get Your Hands Dirty!"





Florence Reeder

An introduction to MT evaluation [PDF of PPT]

Jumping off points: ideas of possible tasks [PDF of PPT]

Basic rules of engagement: desired output of workshop teams [PDF of PPT]

NAACL Workshop on MTE, June 3, 2001 [PDF of PPT]

Fightin’ words: points for discussion [PDF of PPT]

Maghi King

Standards work related to evaluation [PDF].

John White

MT evaluation: the DARPA measures and MT proficiency scale [PDF of PPT]

Andrei Popescu-Belis

Formal framework for NLP evaluation [not available].

Tentative conclusion of the workshop [not available].

Widad Mustafa El Hadi, Ismaël Timimi, Marianne Dabbadie

Evaluating an MT French/English system. [PDF of PPT]

Marie-Jo Astre, Anna Civil, Francine Braun-Chen, Marianne Starlander, Elia Yuste

Comparative evaluation of the linguistic output of MT systems for translation and non-translation purposes. [PDF of PPT]; table [PDF of Excel]

Palmira Marrafa and António Ribeiro

Quantitative evaluation of machine translation systems: sentence level. [PDF of PPT]

Tony Hartley and Martin Rajman  

Predicting MT fluency from IE precision and recall. [PDF of PPT]

Donna M.Gates, Josemina Magdalen, Keith Miller, Nancy L.Underwood

Evaluating an MT system without knowledge of the source language. [PDF of PPT]

Christine Bruckner and Mirko Plitt

Evaluating the operational benefit of using machine translation output as translation memory input in the translation process of software documentation. [PDF]

John White and Monika Forner

Correlation of translation phenomena and fidelity measures. [PDF of PPT]