DiQAD: A Benchmark Dataset for Open-domain Dialogue Quality Assessment

Yukun Zhao, Lingyong Yan, Weiwei Sun, Chong Meng, Shuaiqiang Wang, Zhicong Cheng, Zhaochun Ren, Dawei Yin

Submission Type: Regular Long Paper

Submission Track: Resources and Evaluation

Submission Track 2: Dialogue and Interactive Systems

Keywords: Dataset, Dialogue Evaluation Dataset, Dialogue Quality Assessment, Dialogue Quality Evaluation, Dialogue Quality Benchmark, Dialogue Evaluation

Abstract:

Dialogue assessment plays a critical role in the development of open-domain dialogue systems.
Existing work are uncapable of providing an end-to-end and human-epistemic assessment dataset, while they only provide sub-metrics like coherence or the dialogues are conversed between annotators far from real user settings.
In this paper, we release a large-scale dialogue quality assessment dataset (DiQAD), for automatically assessing open-domain dialogue quality.
Specifically, we (1) establish the assessment criteria based on the dimensions conforming to human judgements on dialogue qualities, and (2) annotate large-scale dialogues that conversed between real users based on these annotation criteria, which contains around 100,000 dialogues.
We conduct several experiments and report the performances of the baselines as the benchmark on DiQAD.
The dataset is openly accessible at \url{https://github.com/yukunZhao/Dataset_Dialogue_quality_evaluation}.

Submission Number: 3313