Response Quality

AbstractEvaluating open-domain dialogue systems is difficult due to the diversity of possible correct answers. Automatic metrics such as BLEU correlate weakly with human annotations, resulting in a significant bias across …...

AbstractTraining the generative models with minimal corpus is one of the critical challenges for building open-domain dialogue systems. Existing methods tend to use the meta-learning framework which pre-trains the parameters …...

AbstractHuman conversations contain natural and reasonable topic shifts, reflected as the concept flows across utterances. Previous researches prove that explicitly modeling concept flows with a large commonsense knowledge graph effectively …...