The SDL language weaver systems in the WMT12 quality estimation shared task

Authors:
Radu Soricut;Nguyen Bach;Ziyuan Wang
Affiliations:
SDL Language Weaver, Los Angeles, CA;SDL Language Weaver, Los Angeles, CA;SDL Language Weaver, Los Angeles, CA
Venue:
WMT '12 Proceedings of the Seventh Workshop on Statistical Machine Translation
Year:
2012

Citing 5
Cited 7

Moses: open source toolkit for statistical machine translation

ACL '07 Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions
TrustRank: inducing trust in automatic translations via ranking

ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Goodness: a method for measuring machine translation confidence

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Findings of the 2012 workshop on statistical machine translation

WMT '12 Proceedings of the Seventh Workshop on Statistical Machine Translation
Combining quality prediction and system selection for improved automatic translation output

WMT '12 Proceedings of the Seventh Workshop on Statistical Machine Translation

Findings of the 2012 workshop on statistical machine translation

WMT '12 Proceedings of the Seventh Workshop on Statistical Machine Translation
Quality estimation for machine translation: some lessons learned

Machine Translation
Sentence-level ranking with quality estimation

Machine Translation
Dimensionality reduction methods for machine translation quality estimation

Machine Translation
Predicting sentence translation quality using extrinsic and language independent features

Machine Translation
Investigating the contribution of linguistic information to quality estimation

Machine Translation
Weakly supervised approaches for quality estimation

Machine Translation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present in this paper the system submissions of the SDL Language Weaver team in the WMT 2012 Quality Estimation shared-task. Our MT quality-prediction systems use machine learning techniques (M5P regression-tree and SVM-regression models) and a feature-selection algorithm that has been designed to directly optimize towards the official metrics used in this shared-task. The resulting submissions placed 1st (the M5P model) and 2nd (the SVM model), respectively, on both the Ranking task and the Scoring task, out of 11 participating teams.