KG-BERTScore: Incorporating Knowledge Graph into BERTScore for Reference-Free Machine Translation Evaluation
Abstract
BERTScore is an effective and robust automatic metric for referencebased machine translation evaluation. In this paper, we incorporate multilingual knowledge graph into BERTScore and propose a metric named KG-BERTScore, which linearly combines the results of BERTScore and bilingual named entity matching for reference-free machine translation evaluation. From the experimental results on WMT19 QE as a metric without references shared tasks, our metric KG-BERTScore gets higher overall correlation with human judgements than the current state-of-the-art metrics for reference-free machine translation evaluation.1 Moreover, the pre-trained multilingual model used by KG-BERTScore and the parameter for linear combination are also studied in this paper.
Cite
@article{arxiv.2301.12699,
title = {KG-BERTScore: Incorporating Knowledge Graph into BERTScore for Reference-Free Machine Translation Evaluation},
author = {Zhanglin Wu and Min Zhang and Ming Zhu and Yinglu Li and Ting Zhu and Hao Yang and Song Peng and Ying Qin},
journal= {arXiv preprint arXiv:2301.12699},
year = {2023}
}
Comments
5 pages