BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation

TL;DR

BlonDe is a new automatic evaluation metric for document-level machine translation that considers discourse coherence and correlates better with human judgments than existing metrics.

Contribution

The paper introduces BlonDe, a novel metric that evaluates document-level translation quality by incorporating discourse phenomena, improving over sentence-level metrics.

Findings

BlonDe outperforms existing metrics in correlation with human judgments.

BlonDe effectively captures document-level discourse phenomena.

Experimental results demonstrate its higher sensitivity and interpretability.

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 BlonDe possesses better selectivity and interpretability at the document-level, and is more sensitive to document-level nuances. In a large-scale human study, BlonDe also achieves significantly higher Pearson's r correlation with human judgments compared to previous metrics.