论文标题
知识桥接善解人意的对话生成
Knowledge Bridging for Empathetic Dialogue Generation
论文作者
论文摘要
缺乏外部知识使善解人意的对话系统难以感知隐性情绪并从有限的对话历史中学习情感互动。为了解决上述问题，我们建议利用外部知识，包括常识性知识和情感词汇知识，以明确理解和表达同理心对话生成中的情绪。我们首先通过与外部知识共同互动并构建情感上下文图来丰富对话历史。然后，我们从富含知识的情感上下文图和提取情感信号中学习情感上下文表示，这是谓词在响应中表达的谓词的先决条件。最后，为了产生善解人意的反应，我们提出了一种情感跨注意机制，以从情感上下文图中学习情感依赖性。在基准数据集上进行的广泛实验验证了所提出的方法的有效性。此外，我们发现，通过与正交作用的预训练模型集成，可以进一步提高我们的方法的性能。
Lack of external knowledge makes empathetic dialogue systems difficult to perceive implicit emotions and learn emotional interactions from limited dialogue history. To address the above problems, we propose to leverage external knowledge, including commonsense knowledge and emotional lexical knowledge, to explicitly understand and express emotions in empathetic dialogue generation. We first enrich the dialogue history by jointly interacting with external knowledge and construct an emotional context graph. Then we learn emotional context representations from the knowledge-enriched emotional context graph and distill emotional signals, which are the prerequisites to predicate emotions expressed in responses. Finally, to generate the empathetic response, we propose an emotional cross-attention mechanism to learn the emotional dependencies from the emotional context graph. Extensive experiments conducted on a benchmark dataset verify the effectiveness of the proposed method. In addition, we find the performance of our method can be further improved by integrating with a pre-trained model that works orthogonally.
