BERTScore: Evaluating Text Generation with BERT
Abstract
We propose BERTScore, an automatic evaluation metric for text generation. Analogously to common metrics, BERTScore computes a similarity score for each token in the candidate sentence with each token in the reference sentence. However, instead of exact matches, we compute token similarity using contextual embeddings. We evaluate using the outputs of 363 machine translation and image captioning systems. BERTScore correlates better with human judgments and provides stronger model selection performance than existing metrics. Finally, we use an adversarial paraphrase detection task to show that BERTScore is more robust to challenging examples when compared to existing metrics.
Cite
@article{arxiv.1904.09675,
title = {BERTScore: Evaluating Text Generation with BERT},
author = {Tianyi Zhang and Varsha Kishore and Felix Wu and Kilian Q. Weinberger and Yoav Artzi},
journal= {arXiv preprint arXiv:1904.09675},
year = {2020}
}
Comments
Code available at https://github.com/Tiiiger/bert_score; To appear in ICLR2020