BLEURT: Learning Robust Metrics for Text Generation

Understand

Text generation has made significant advances in the last few years.

• Yet, evaluation metrics have lagged behind, as the most popular choices (e.g., BLEU and ROUGE) may correlate poorly with human judgments.
• We propose BLEURT, a learned evaluation metric based on BERT that can model human judgments with a few thousand possibly biased training examples.
• A key aspect of our approach is a novel pre-training scheme that uses millions of synthetic examples to help the model generalize.