Abstract
The Multi-Engine MT (MEMT) architecture combines the outputs of multiple MT engines using a statistical language model of the target language. It has been used successfully in a number of MT research systems, for both text and speech translation. Despite its perceived benefits, there has never been a rigorous, published, double-blind evaluation of the claim that the combined output of a MEMT system is in fact better than that of any one of the component MT engines. We report here the results of such an evaluation. The combined MEMT output is shown to indeed be better overall than the output of the component engines in a Croatian ↔ English MT system. This result is consistent in both translation directions, and between different raters.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
J. J. Bartko and W. T. Carpenter. 1976. On the Methods and Theory of Reliability. The Journal of Nervous and Mental Disease, 163(5):307–317.
I. N. Bronstein and K. A. Semendyayev. 1985. Handbook of Mathematics. Verlag Harri Deutsch, Thun and Frankfurt/Main, Frankfurt/Main, third edition.
Ralf Brown and Robert Frederking. 1995. Applying Statistical English Language Modeling to Symbolic Machine Translation. In Proceedings of the Sixth International Conference on Theoretical and Methodological Issues in Machine Translation (TMI-95), pages 221–239.
Ralf Brown. 1996. Example-based Machine Translation in the Pangloss System. In Proceedings of the 16th International Conference on Computational Linguistics (COLING-96).
David Carter et al. 1997. Translation Methodology in the Spoken Language Translator: An Evaluation. In Steven Krauwer et al., editors, Spoken Language Translation: Proceedings of a Workshop, pages 73–81, Madrid, Spain, July. Association of Computational Linguistics and European Network in Language and Speech.
G. Dunn. 1989. Design and Analysis of Reliability Studies: The Statistical Evaluation of Measurement Errors. Oxford University Press, New York.
David Farwell and Yorick Wilks. 1991. Ultra: A Multi-Lingual Machine Translator. In Proceedings of Machine Translation Summit III, Washington D. C., July.
Robert Frederking and Ralf Brown. 1996. The Pangloss-Lite Machine Translation System. In Proceedings of the Second Conference of the Association for Machine Translation in the Americas (AMTA), pages 268–272, Montreal, Quebec, Canada, October.
Robert Frederking and Sergei Nirenburg. 1994. Three Heads are Better than One. In Proceedings of the Fourth Conference on Applied Natural Language Processing (ANLP-94), Stuttgart, Germany.
Robert Frederking et al. 1993. An MAT Tool and its Effectiveness. In Proceedings of the DARPA Human Language Technology Workshop, Princeton, New Jersey.
Robert Frederking et al. 1994. Integrating Translations from Multiple Sources with the Pangloss Mark III Machine Translation System. In Proceedings of the First Conference for Machine Translation in the Americas (AMTA), Columbia, Maryland, October.
Robert Frederking, Alexander Rudnicky, and Christopher Hogan. 1997. Interactive Speech Translation in the DIPLOMAT Project. In Steven Krauwer et al., editors, Spoken Language Translation: Proceedings of a Workshop, pages 61–66, Madrid, Spain, July. Association of Computational Linguistics and European Network in Language and Speech.
Robert Frederking. 1994. Statistical Language Models for Symbolic MT. In Language Engineering on the Information Highway Workshop, Santorini, Greece, September.
Donna Gates et al. 1996. End-to-End Evaluation in Janus: A Speech-to-Speech Translation System. In Elisabeth Maier et al., editors, Dialogue Processing in Spoken Language Systems, volume 1236 of Lecture Notes in Artificial Intelligence, pages 195–206. Springer-Verlag, Berlin.
Juliane House. 1981. A Model for Translation Quality Assessment. Gunter Narr Verlag.
Martin Kay. 1967. Experiments with a Powerful Parser. In Proceedings of the 2nd International COLING, August.
K. Krippendorf. 1970. Bivariate Agreement Coeffcients for Reliability of Data. In E. F. Borgatta and G. W. Bohrnstedt, editors, Sociological Methodology. Jossey-Bass, San Francisco.
R. J. Light. 1971. Measures of Response Agreement for Qualitative Data: Some Generalizations and Alternatives. Psychological Bulletin, 76:365–377.
R. R. MacDonald. 1963. General Report 1952-1963. Number 30 in Georgetown University Occasional Papers in Machine Translation. Washington, D. C.
A. K. Melby. 1983. Computer-Assisted Translation Systems: The Standard Design and a Multi-Level Design. In Conference on Applied Natural Language Processing, Santa Monica, California, February.
Teruko Mitamura, Eric Nyberg, and Jaime Carbonell. 1991. Interlingua Translation System for Multi-Lingual Document Processing. In Proceedings of Machine Translation Summit III, Washington, D. C., July.
M. Nagao. 1984. A Framework of a Mechanical Translation between Japanese and English by Analogy Principle. In A. Elithorn and R. Banerji, editors, Artificial and Human Intelligence. NATO Publications.
Sergei Nirenburg et al. 1995. The Pangloss Mark III Machine Translation System. Technical Report Issued as CMU Technical Report CMU-CMT-95-145, Joint Technical Report, Computing Research Laboratory (New Mexico State University), Center for Machine Translation (Carnegie Mellon University), Information Sciences Institute (University of Southern California).
Sergei Nirenburg et al. 1996. Two Principles and Six Techniques for Rapid MT Development. In Proceedings of the Second Conference of the Association for Machine Translation in the Americas, pages 96–105, Montreal, Quebec, Canada, October.
William H. Press, Brian P. Flannery, Saul A. Teukolsky, and William T. Vetterling. 1986. Numerical Recipes: The Art of Scientific Computing. Cambridge University Press, Cambridge, England.
Manny Rayner and David Carter. 1997. Hybrid Processing in the Spoken Language Translator. In Proceedings of ICASSP-97, Munich, Germany.
S. Sato and M. Nagao. 1990. Towards Memory Based Translation. In Proceedings of COLING-90, Helsinki, Finland.
J. S. White and T. A. O’Connell. 1994. The ARPA MT Evaluation Methodologies: Evolution, Lessons, and Future Approaches. In Proceedings of the First Conference of the Association for Machine Translation in the Americas (AMTA).
Terry Winograd. 1983. SyntaxLanguage as a Cognitive Process. Volume 1: Syntax. Addison-Wesley.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hogan, C., Frederking, R.E. (1998). An Evaluation of the Multi-engine MT Architecture. In: Farwell, D., Gerber, L., Hovy, E. (eds) Machine Translation and the Information Soup. AMTA 1998. Lecture Notes in Computer Science(), vol 1529. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-49478-2_11
Download citation
DOI: https://doi.org/10.1007/3-540-49478-2_11
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65259-5
Online ISBN: 978-3-540-49478-2
eBook Packages: Springer Book Archive