Abstract
Translations produced by an MT system can automatically be assigned a number that reflects the MT system’s confidence in their quality. We describe the design of such a confidence index, with focus on the contribution of source analysis, which plays a crucial role in many MT systems, including ours. Various problematic areas of source analysis are identified, and their impact on the overall confidence index is given. We will describe two methods of training the confidence index, one by hand-tuning of the heuristics, the other by linear regression analysis.
A system that measures the translatability of a complete document is described in [8].
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bernth, A.: EasyEnglish: A tool for improving document quality. In Proceedings of the Fifth Conference on Applied Natural Language Processing. Association for Computational Linguistics (1997) 159–165
Bernth, A.: EasyEnglish: Addressing structural ambiguity. In Proceedings of AMTA-98. Association for Machine Translation in the Americas (1998) 164–173
Bernth, A.: EasyEnglish: Preprocessing for MT. In Proceedings of the Second International Workshop on Controlled Language Applications. (1998) CarnegieMellon University. Pittsburgh, PA 30–41
Bernth, A.: A confidence index for machine translation. In Proceedings of Theoretical and Methodological Issues in Machine Translation. Chester, England (1999) 120–127
Bernth, A.: Controlling input and output of MT for greater user acceptance. In Proceedings 21st Conference Translating and the Computer. (1999)
Bernth, A.: Tools for improving E-G MT quality. In Proceedings of Theoretical and Methodological Issues in Machine Translation, Workshop on Problems and Potential of English-to-German MT Systems. Chester, England (1999)
Bernth, A.: EasyEnglish: Grammar checking for non-native speakers. In Proceedings of the Third International Workshop on Controlled Language Applications. Seattle, WA (2000) 33–42
Gdaniec, C.: The Logos translatability index. In Proceedings of AMTA-94. Association for Machine Translation in the Americas (1994) 97–105.
Gdaniec, C.: Lexical choice and syntactic generation in a transfer system: Transformations in the new LMT English-German system. In Proceedings of AMTA-98. Association for Machine Translation in the Americas (1998) 408–420.
Lewis, D.: MT evaluation: Science or art? In Proceedings 19st Conference Translating and the Computer. (1997) 1–14
McCord, M.: Slot Grammars. Computational Linguistics. 6 (1980) 31–43
McCord, M.: Slot Grammar: A system for simpler construction of practical natural language grammars. In R. Studer, (ed.), Natural Language and Logic: International Scientific Symposium, Lecture Notes in Computer Science. Springer Verlag, Berlin (1990) 118–145
McCord, M.: Heuristics for broad-coverage natural language parsing. In Proceedings of the ARPA Human Language Technology Workshop. Morgan-Kaufmann (1993) 127–132
McCord, M. and Bernth, A.: The LMT transformational system. In Proceedings of AMTA-98. Association for Machine Translation in the Americas (1998) 344–355
Pierce, J.R., Carroll, J.B., et al.: Language and machines: Computers in translation and linguistics. Technical Report 1416, Automated Language Processing Advisory Committee (ALPAC), National Academy of Sciences, National Research Council, Washington, D.C. (1966)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bernth, A., McCord, M.C. (2000). The Effect of Source Analysis on Translation Confidence. In: White, J.S. (eds) Envisioning Machine Translation in the Information Future. AMTA 2000. Lecture Notes in Computer Science(), vol 1934. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-39965-8_9
Download citation
DOI: https://doi.org/10.1007/3-540-39965-8_9
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41117-8
Online ISBN: 978-3-540-39965-0
eBook Packages: Springer Book Archive