BLEURT: Learning Robust Metrics for Text Generation
It addresses the need for better evaluation metrics in text generation, which is crucial for researchers and practitioners, though it is an incremental improvement over existing BERT-based methods.
The paper tackles the problem of evaluating text generation by proposing BLEURT, a learned metric based on BERT that models human judgments, achieving state-of-the-art results on WMT Metrics and WebNLG datasets.
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. BLEURT provides state-of-the-art results on the last three years of the WMT Metrics shared task and the WebNLG Competition dataset. In contrast to a vanilla BERT-based approach, it yields superior results even when the training data is scarce and out-of-distribution.