KG-BERTScore: Incorporating Knowledge Graph into BERTScore for Reference-Free Machine Translation Evaluation
This work addresses the need for better automatic evaluation metrics in machine translation, particularly in reference-free scenarios, though it is incremental as it builds on existing BERTScore and named entity matching methods.
The paper tackles the problem of reference-free machine translation evaluation by incorporating a multilingual knowledge graph into BERTScore, resulting in KG-BERTScore, which achieves higher correlation with human judgments than current state-of-the-art metrics on the WMT19 benchmark.
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.