A quantitative method for machine translation evaluation

Authors:
Jesús Tomás;Josep Àngel Mas;Francisco Casacuberta
Affiliations:
Universitat Politècnica de València;Universitat Politècnica de València;Universitat Politècnica de València
Venue:
Evalinitiatives '03 Proceedings of the EACL 2003 Workshop on Evaluation Initiatives in Natural Language Processing: are evaluation methods, metrics and resources reusable?
Year:
2003

Citing 3
Cited 0

A statistical approach to machine translation

Computational Linguistics
Finite-State Speech-to-Speech Translation

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97) -Volume 1 - Volume 1
BLEU: a method for automatic evaluation of machine translation

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Accurate evaluation of machine translation (MT) is an open problem. A brief survey of the current approach to tackle this problem is presented and a new proposal is introduced. This proposal attempts to measure the percentage of words, which should be modified at the output of an automatic translator in order to obtain a correct translation. To show the feasibility of the method we have assessed the most important Spanish-Catalan translators in comparing the results obtained by the various methods.