UGENT-LT3 SCATE System for Machine Translation Quality Estimation

By Arda Tezcan, Veronique Hoste, Bart Desmet, Lieve Macken. 2015

10 citations recorded by the source corpus.

This paper describes the submission of the UGENT-LT3 SCATE system to the WMT15 Shared Task on Quality Estimation (QE), viz. English-Spanish word and sentence-level QE. We conceived QE as a supervised Machine Learning (ML) problem and designed additional features and combined these with the baseline feature set to estimate quality. The sentence-level QE system re-uses the word level predictions of the word-level QE system. We experimented with different learning methods and observe improvements over the baseline system for wordlevel QE with the use of the new features and by combining learning methods into ensembles. For sentence-level QE we show that using a single feature based on word-level predictions can perform better than the baseline system and using this in combination with additional features led to further improvements in performance.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Lieve Macken
2. Veronique Hoste
3. Arda Tezcan

Citations in the corpus

• Findings of the 2015 Workshop on Statistical Machine Translation (2015, neutral): “, 2015a) UGENT Ghent University, Belgium (Tezcan et al., 2015) USAAR-USHEF University of Sheffield, UK and Saarland University, Germany (Scarton et al.”
• UGENT-LT3 SCATE Submission for WMT16 Shared Task on Quality Estimation (2016, methodology): “…each target word of the MT output, in addition to the provided baseline features, which were described in the WMT15 QE shared task (Bojar et al., 2015), we extracted the features we used for our last year’s submission, for which detailed descriptions can be found in Tezcan et al. (2015).”