xDial-Eval: A Multilingual Open-Domain Dialogue Evaluation Benchmark
This work addresses the problem of evaluating dialogue systems across multiple languages for researchers and developers, though it is incremental as it builds on existing English datasets and methods.
The authors tackled the lack of a multilingual benchmark for evaluating open-domain dialogue systems by introducing xDial-Eval, which extends English datasets to nine other languages via machine translation, and their best baseline model achieved absolute improvements of 6.5% and 4.6% over ChatGPT in average Pearson correlations at turn and dialogue levels, respectively.
Recent advancements in reference-free learned metrics for open-domain dialogue evaluation have been driven by the progress in pre-trained language models and the availability of dialogue data with high-quality human annotations. However, current studies predominantly concentrate on English dialogues, and the generalization of these metrics to other languages has not been fully examined. This is largely due to the absence of a multilingual dialogue evaluation benchmark. To address the issue, we introduce xDial-Eval, built on top of open-source English dialogue evaluation datasets. xDial-Eval includes 12 turn-level and 6 dialogue-level English datasets, comprising 14930 annotated turns and 8691 annotated dialogues respectively. The English dialogue data are extended to nine other languages with commercial machine translation systems. On xDial-Eval, we conduct comprehensive analyses of previous BERT-based metrics and the recently-emerged large language models. Lastly, we establish strong self-supervised and multilingual baselines. In terms of average Pearson correlations over all datasets and languages, the best baseline outperforms OpenAI's ChatGPT by absolute improvements of 6.5% and 4.6% at the turn and dialogue levels respectively, albeit with much fewer parameters. The data and code are publicly available at https://github.com/e0397123/xDial-Eval.