Merging example-based and statistical machine translation: an experiment

Philippe Langlais, Michel Simard


Abstract
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 [6], 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.
Anthology ID:
2002.amta-papers.11
Volume:
Proceedings of the 5th Conference of the Association for Machine Translation in the Americas: Technical Papers
Month:
October 8-12
Year:
2002
Address:
Tiburon, USA
Editor:
Stephen D. Richardson
Venue:
AMTA
SIG:
Publisher:
Springer
Note:
Pages:
104–113
Language:
URL:
https://link.springer.com/chapter/10.1007/3-540-45820-4_11
DOI:
Bibkey:
Cite (ACL):
Philippe Langlais and Michel Simard. 2002. Merging example-based and statistical machine translation: an experiment. In Proceedings of the 5th Conference of the Association for Machine Translation in the Americas: Technical Papers, pages 104–113, Tiburon, USA. Springer.
Cite (Informal):
Merging example-based and statistical machine translation: an experiment (Langlais & Simard, AMTA 2002)
Copy Citation:
PDF:
https://link.springer.com/chapter/10.1007/3-540-45820-4_11