Despite the exciting work accomplished over the past decade in the field of Statistical Machine Translation (SMT), we are still far from the point of being able to say that machine translation fully meets the needs of real-life users. In a previous study , we have shown how a SMT engine could benefit from terminological resources, especially when translating texts very different from those used to train the system. In the present paper, we discuss the opening of SMT to examples automatically extracted from a Translation Memory (TM). We report results on a fair-sized translation task using the database of a commercial bilingual concordancer.
- Machine Translation
- Statistical Machine Translation
- Word Error Rate
- Airline Industry
- Translation Memory
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, access via your institution.
Unable to display preview. Download preview PDF.
Anne Abeillé, Lionel Clément and Alexandra Kinyon. Building a treebank for French. International Conference on Language Resources & Evaluation (LREC), Athens, Greece (2000).
Peter F. Brown, Stephen A. Della Pietra, Vincent J. Della Pietra and Robert L. Mercer. The Mathematics of Machine Translation: Parameter Estimation. Computational Linguistics, 19-2 (1993) 263–311.
Ralf D. Brown. Example-Based Machine Translation in the Pangloss System. International Conference on Computational Linguistics (COLING), Copenhagen, Denmark, (1996) 169–174.
Michael Carl and Silvia Hansen. Linking Translation Memories with Example-Based Machine Translation. Machine Translation Summit VII, Singapore (1999) 617–624.
George F. Foster. Statistical Lexical Disambiguation. MSc thesis, McGill University, School of Computer Science (1991).
Philippe Langlais. Opening Statistical Translation Engines to Terminological Resources. 7th International Workshop on Applications of Natural Language to Information Systems (NLDB). June 27–28, 2002. Stockholm, Sweden (2002).
Elliot Macklovitch and Graham Russell. What’s been Forgotten in Translation Memory. The Association for Machine Translation in the Americas (AMTA-2000), Cuer-navaca, Mexico (2000).
Elliott Macklovitch, Michel Simard and Philippe Langlais. TransSearch: A Free Translation Memory on the World Wide Web. International Conference on Language Resources & Evaluation (LREC), Athens, Greece (2000) 641–648.
Daniel Marcu. Towards a Unified Approach to Memory-and Statistical-Based Machine Translation. Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics, Toulouse, France (2001) 378–385.
S. Niessen, S. Vogel, H. Ney and C. Tillmann. A DP based Search Algorithm for Statistical Machine Translation. COLING/ACL (1998) 960–966.
Miles Osborne. Shallow Parsing as Part-of-Speech Tagging. Proceedings of CoNLL, Lisbon, Portugal (2002).
Michel Simard, George Foster and Pierre Isabelle. Using Cognates to Align Sentences in Bilingual Corpora. Conference on Theoretical and Methodological Issues in Machine Translation (TMI), Montréal, Québec (1992) 67–82.
Michel Simard and Philippe Langlais. Sub-sentential Exploitation of Translation Memories. MTSummit-VIII, Santiago de Compostela, Spain, (2001) 335–340.
Editors and Affiliations
Rights and permissions
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Langlais, P., Simard, M. (2002). Merging Example-Based and Statistical Machine Translation: An Experiment. In: Richardson, S.D. (eds) Machine Translation: From Research to Real Users. AMTA 2002. Lecture Notes in Computer Science(), vol 2499. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45820-4_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-44282-0
Online ISBN: 978-3-540-45820-3
eBook Packages: Springer Book Archive