Positively transitioned sentiment dialogue corpus for developing emotion-affective open-domain chatbots
This work addresses the need for more emotionally responsive chatbots, though it appears incremental as it builds on existing dialogue models and data enhancement techniques.
The authors tackled the problem of developing emotion-affective open-domain chatbots by constructing a dialogue corpus with positively transitioned sentiment data and fine-tuning a pretrained model, resulting in close-to-human performance in emotion-affective metrics compared to SOTA chatbots.
In this paper, we describe a data enhancement method for developing Emily, an emotion-affective open-domain chatbot. The proposed method is based on explicitly modeling positively transitioned (PT) sentiment data from multi-turn dialogues. We construct a dialogue corpus with PT sentiment data and will release it for public use. By fine-tuning a pretrained dialogue model using the produced PT-enhanced dialogues, we are able to develop an emotion-affective open-domain chatbot exhibiting close-to-human performance in various emotion-affective metrics. We evaluate Emily against a few state-of-the-art (SOTA) open-domain chatbots and show the effectiveness of the proposed approach. The corpus is made publicly available.