Publication
Comparative Quality Estimation for Machine Translation: Observations on machine learning and features
Eleftherios Avramidis
In: The Prague Bulletin of Mathematical Linguistics (PBML), Vol. 108, Pages 307-318, Charles University, Prague, Czech Republic, 5/2017.
Abstract
A deeper analysis on Comparative Quality Estimation is presented by extending
the state-of-the-art methods with adequacy and grammatical features from other
Quality Estimation tasks.
The previously used linear method, unable to cope with the augmented features,
is replaced with a boosting classifier, assisted by feature selection.
The methods indicated show improved performance for 6 language pairs, when
applied on the output from MT systems developed over 7 years. The improved
models compete better with reference-aware metrics.
Notable conclusions are reached through the examination of the contribution of
the features in the models, whereas it is possible to identify common MT errors
that are captured by the features. Many grammatical/fluency features have a good
contribution, few adequacy features have some contribution, whereas source
complexity features are of no use. The importance of many fluency and adequacy
features is language-specific.