In authors or contributors

1 resource

  • Tianyi Zhang, Varsha Kishore, Felix Wu
    |
    Feb 24th, 2020
    |
    preprint
    Tianyi Zhang, Varsha Kishore, Felix Wu
    Feb 24th, 2020

    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...

Last update from database: 28/12/2024, 07:15 (UTC)
Powered by Zotero and Kerko.