Training a Sentence-Level Machine Translation Confidence Measure

Christopher B. Quirk


Abstract
We present a supervised method for training a sentence level confidence measure on translation output using a human-annotated corpus. We evaluate a variety of machine learning methods. The resultant measure, while trained on a very small dataset, correlates well with human judgments, and proves to be effective on one task based evaluation. Although the experiments have only been run on one MT system, we believe the nature of the features gathered are general enough that the approach will also work well on other systems.
Anthology ID:
L04-1250
Volume:
Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04)
Month:
May
Year:
2004
Address:
Lisbon, Portugal
Editors:
Maria Teresa Lino, Maria Francisca Xavier, Fátima Ferreira, Rute Costa, Raquel Silva
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
Language:
URL:
http://www.lrec-conf.org/proceedings/lrec2004/pdf/426.pdf
DOI:
Bibkey:
Cite (ACL):
Christopher B. Quirk. 2004. Training a Sentence-Level Machine Translation Confidence Measure. In Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04), Lisbon, Portugal. European Language Resources Association (ELRA).
Cite (Informal):
Training a Sentence-Level Machine Translation Confidence Measure (Quirk, LREC 2004)
Copy Citation:
PDF:
http://www.lrec-conf.org/proceedings/lrec2004/pdf/426.pdf