本篇論文著重在移情對話生成任務上。先前研究關於移情對話生成的方法 [1,2]主要集中在檢測和利用用戶的情緒來產生移情反應。本研究將使用額外的常識知識圖譜做為機器人對常識性的背景知識。我們針對非預訓練和預訓練模型各使用不同的方式增強多樣性，在非預訓練模型上我們將 AdaLabel[3] 應用在 CEM 模型[4]上，而對於預訓練模型使用 BART 模型結合多種常識知識讓模型能生成更有資訊的移情回應。研究結果顯示所提出的兩個模型在EMPATHETICDIALOGUES 和 DailyDialog 資料集上都優於基線模型，並且在個案研究中可以看到模型產生更多信息和同理心的回應。 ;To improve students’ expression and language ability in education, listening and reading English short stories can be used to allow students to extend from talking about the content of the stories to their personal experiences and feelings in daily life, but this process requires a lot of teacher and time, so We plan to build a Story Chatbot, in addition to story-related Q&A, can also respond with empathy to daily conversation. Previous approaches on empathetic response generation have mainly focused on detecting and exploiting users emotions to generate empathetic responses. In this study, the additional commonsense knowledge graph is used as the background knowledge of commonsense for robots, and in order to be practically applied in schools, it is necessary to improve the generation diversity of the model. We use different ways to enhance diversity for non-pre-trained and pre-trained models. For non-pre-trained models, we apply AdaLabel [3] to CEM model [4], and for pretrained models, we use the BART model combined with a variety of common sense knowledge to allow the model to generate more Informative empathetic responses. The results show that the two proposed models outperform the baseline models on both the EMPATHETICDIALOGUES and DailyDialog datasets, and in the case study model can be seen to generate more informative and empathetic responses.
