Abstract
When surveying the many methods currently employed in MT evaluation,1 it is not immediately obvious that the methods used serve to increase the knowledge of the properties being measured. This report describes aconstructive machine translation evaluation method, aimed at addressing this issue.2
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Balfour, Richard. W. (1986). Machine Translation: A Technology Assessment: An Introduction, an Evaluation, and a Study of Market Position Present and Future,BMT Consultants, London.
Finkelstein, L., Leaning, M.S. (1984). A Review of the Fundamental Concept of Measurement.Measurement, 2(1): 25–34, 1984.
Lehrberger, J., Bourbeau, L. 1988. Machine Translation: Linguistic Characteristics of MT Systems and General Methodology of Evaluation,John Benjamins Publishing Company, Amsterdam/Philadelphia.
Nagao, M., Tsujii, J., and Nakamura, J. 1988. The Japanese Government Project for Machine Translation,Machine Translation Systems, pp. 141–186, Edited by Jonathan Slocum, Cambridge University Press.
Takayama, Y., Suzuki K., Maruyama, F., and Dasai, T. 1991. A Prolog-based MT System, MELTRAN J/E, Pacific Rim Conference on Natural Language Processing.
Author information
Authors and Affiliations
Additional information
Edited version of a presentation given to the International Working Group on the Evaluation of Machine Translation Systems, Vaud, Switzerland, April 1991.
Rights and permissions
About this article
Cite this article
Minnis, S. Constructive machine translation evaluation. Mach Translat 8, 67–75 (1993). https://doi.org/10.1007/BF00981244
Issue Date:
DOI: https://doi.org/10.1007/BF00981244