PEAR: Pairwise Evaluation for Automatic Relative Scoring in Machine Translation
Researchers have developed PEAR, a novel supervised quality estimation metric for machine translation that reframes evaluation as a pairwise comparison. This method predicts the direction and magnitude of quality differences between two candidate translations. PEAR outperforms existing metrics, including larger models and reference-based approaches, despite using fewer parameters. It also proves effective for minimum Bayes risk decoding, reducing computational costs with minimal impact on performance. AI
IMPACT Introduces a more efficient and effective method for evaluating machine translation quality, potentially improving decoding strategies.