Paper: A New Quantitative Quality Measure For Machine Translation Systems

ACL ID C92-2067
Title A New Quantitative Quality Measure For Machine Translation Systems
Venue International Conference on Computational Linguistics
Session Main Conference
Year 1992
Authors

In this paper, an objective qtumtitative quality mea- sure is proposed to evaluate tile performance of machiue translation systems. The proposed method is to compare the raw translation output of an MT system with the fi- nal revised version lor the customers, and then compute the editing efforts required to convert the raw translation to the final version. In contrast to the other prolx)sals, the evaluatiral process can he (lone quickly and auto- matically. Itence, it can provide a quick response on any system change. A system designer can thus quickly lind the advantages or faults of a particular performance- improving strategy aml improve system performance dy- namieally. Application of such a measure to improve the system performance on-line on a parameterized and feedback-controlled s...