Breeding Machine Translations: Evolutionary approach to survive and thrive in the world of automated evaluation
This work addresses the challenge of automated evaluation in machine translation, offering a novel approach to enhance quality and detect metric vulnerabilities, though it is incremental in applying evolutionary techniques to this domain.
The authors tackled the problem of improving machine translation quality and identifying weaknesses in evaluation metrics by proposing a genetic algorithm-based method that modifies n-best lists, resulting in increased translation quality as measured by held-out metrics and exposing flaws in metrics like COMET.
We propose a genetic algorithm (GA) based method for modifying n-best lists produced by a machine translation (MT) system. Our method offers an innovative approach to improving MT quality and identifying weaknesses in evaluation metrics. Using common GA operations (mutation and crossover) on a list of hypotheses in combination with a fitness function (an arbitrary MT metric), we obtain novel and diverse outputs with high metric scores. With a combination of multiple MT metrics as the fitness function, the proposed method leads to an increase in translation quality as measured by other held-out automatic metrics. With a single metric (including popular ones such as COMET) as the fitness function, we find blind spots and flaws in the metric. This allows for an automated search for adversarial examples in an arbitrary metric, without prior assumptions on the form of such example. As a demonstration of the method, we create datasets of adversarial examples and use them to show that reference-free COMET is substantially less robust than the reference-based version.