In the realm of human-AI dialogue, the facilitation of empathetic responses
is important. Validation is one of the key communication techniques in
psychology, which entails recognizing, understanding, and acknowledging others'
emotional states, thoughts, and actions. This study introduces the first
framework designed to engender empathetic dialogue with validating responses.
Our approach incorporates a tripartite module system: 1) validation timing
detection, 2) users' emotional state identification, and 3) validating response
generation. Utilizing Japanese EmpatheticDialogues dataset - a textual-based
dialogue dataset consisting of 8 emotional categories from Plutchik's wheel of
emotions - the Task Adaptive Pre-Training (TAPT) BERT-based model outperforms
both random baseline and the ChatGPT performance, in term of F1-score, in all
modules. Further validation of our model's efficacy is confirmed in its
application to the TUT Emotional Storytelling Corpus (TESC), a speech-based
dialogue dataset, by surpassing both random baseline and the ChatGPT. This
consistent performance across both textual and speech-based dialogues
underscores the effectiveness of our framework in fostering empathetic human-AI
communication.

利用三部分模块系统，包括验证时机检测、用户情绪状态识别和验证式回应生成，本研究介绍了首个旨在促进共情对话的框架。通过利用日本 EmpatheticDialogues 数据集和 Task Adaptive Pre-Training（TAPT）基于 BERT 的模型，在所有模块的 F1 分数方面，表现超过随机基准线和 ChatGPT；在 TUT Emotional Storytelling Corpus（TESC）语音对话数据集上的应用也证实了模型的有效性，超过了随机基准线和 ChatGPT，强调了我们框架在促进人工智能与人类之间的共情沟通上的有效性。