AI engineering glossary · Evaluation metrics
What is BERTScore?
BERTScore: A text-generation metric that embeds each word of the candidate and reference with a pretrained contextual language model and matches words by cosine similarity, then reports precision, recall and F1. It credits paraphrases with different wording, which pure word overlap cannot.
BERTScore: an example
'The film was fantastic' versus the reference 'The movie was great' scores low on word overlap but high on BERTScore, since the embeddings of matching words are close.
Related terms
More Evaluation metrics terms
- Bits per byte
- BLEU
- Brier score
- Calibration
- Calinski-Harabasz index
- Catalogue coverage
- Character error rate
- chrF
Where you learn it
BERTScore is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.