基於常識知識的移情對話回覆生成

Improving Response Diversity through Commonsense-Aware Empathetic Response Generation

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(Majumderet al., 2020b; Lin et al., 2019)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(Wang et al., 2021)應用在CEM模型(Sabour et al., 2022)上，而對於預訓練模型我們使用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。

Due to the lack of conversation practice；the main challenge for the second-language learners is speaking. Our goal is to develop a chatbot to encourage individuals to reflect；describe；analyse and communicate what they read as well as improve students’English expression skills. In this paper；we exploit COMMET；an inferential commonsense knowledge generator；as the background knowledge to improve the generation diversity. We consider two approaches to increase the diversity of empathetic response generation. For nonpretrained models；We apply AdaLabel (Wang et al.；2021) to Commonsense-aware Empathetic model (Sabour et al.；2022) and improve Distinct-2 score from 2.99 to 4.08 on EMPATHETIC DIALOGUES (ED). Furthermore；we augment the pretrained BART model with various commonsense knowledge to generate more informative empathetic responses. Not only has the automatic evaluation of distinct-2 scores improved from 9.11 to 11.21；but the manual case study also shows that CE-BART significantly outperform CEM-AdaLabel.