@inproceedings{jiang2022blonde,
author = {Jiang, Yuchen Eleanor and Liu, Tianyu and Ma, Shuming and Zhang, Dongdong and Yang, Jian and Huang, Haoyang and Sennrich, Rico and Cotterell, Ryan and Sachan, Mrinmaya and Zhou, Ming},
title = {BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation},
booktitle = {NAACL 2022},
year = {2022},
month = {June},
abstract = {Standard automatic metrics, e.g., BLEU, are not reliable for document-level MT evaluation. They can neither distinguish document-level improvements in translation quality from sentence-level ones, nor identify the discourse phenomena that cause context-agnostic translations. This paper introduces a novel automatic metric BlonDe to widen the scope of automatic MT evaluation from sentence to document level. BlonDe takes discourse coherence into consideration by categorizing discourse-related spans and calculating the similarity-based F1 measure of categorized spans. We conduct extensive comparisons on a newly constructed dataset BWB. The experimental results show that BlonD possesses better selectivity and interpretability at the document-level, and is more sensitive to document-level nuances. In a large-scale human study, BlonD also achieves significantly higher Pearson's r correlation with human judgments compared to previous metrics.},
url = {http://approjects.co.za/?big=en-us/research/publication/blonde-an-automatic-evaluation-metric-for-document-level-machine-translation/},
}