Abstract | ||
---|---|---|
We present a machine learning approach to evaluating the well-formedness of output of a machine translation system, using classifiers that learn to distinguish human reference translations from machine translations. This approach can be used to evaluate an MT system, tracking improvements over time; to aid in the kind of failure analysis that can help guide system development; and to select among alternative output strings. The method presented is fully automated and independent of source language, target language and domain. |
Year | DOI | Venue |
---|---|---|
2001 | 10.3115/1073012.1073032 | ACL |
Keywords | Field | DocType |
source language,guide system development,human reference translation,automatic evaluation,target language,mt system,failure analysis,alternative output string,machine translation system,machine translation,machine learning | Rule-based machine translation,Example-based machine translation,Active learning (machine learning),Evaluation of machine translation,Computer science,Synchronous context-free grammar,Machine translation software usability,Transfer-based machine translation,Artificial intelligence,Natural language processing,Virtual finite-state machine,Machine learning | Conference |
Volume | Citations | PageRank |
P01-1 | 32 | 3.10 |
References | Authors | |
9 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Simon Corston-Oliver | 1 | 349 | 25.25 |
Michael Gamon | 2 | 1484 | 89.50 |
Chris Brockett | 3 | 1342 | 66.09 |