Unsupervised Evaluation of Interactive Dialog with DialoGPT
This provides a more interpretable automatic evaluation method for dialog research, addressing a known bottleneck in the field.
The paper tackled the problem of evaluating open-domain dialog systems by introducing FED, an unsupervised metric using DialoGPT to measure fine-grained dialog qualities without ground-truth responses or training data, achieving moderate to strong correlation with human judgment.
It is important to define meaningful and interpretable automatic evaluation metrics for open-domain dialog research. Standard language generation metrics have been shown to be ineffective for dialog. This paper introduces the FED metric (fine-grained evaluation of dialog), an automatic evaluation metric which uses DialoGPT, without any fine-tuning or supervision. It also introduces the FED dataset which is constructed by annotating a set of human-system and human-human conversations with eighteen fine-grained dialog qualities. The FED metric (1) does not rely on a ground-truth response, (2) does not require training data and (3) measures fine-grained dialog qualities at both the turn and whole dialog levels. FED attains moderate to strong correlation with human judgement at both levels.