CausalDialogue：对话中话语级因果关系的建模
CausalDialogue: Modeling Utterance-level Causality in Conversations
AI总结：
本文提出 CausalDialogue 数据集和因果增强损失函数 ExMATE，通过在话语层面建模因果关系来提升神经对话模型生成的多样性与敏捷性，并构建基准验证其效果。
摘要：
尽管神经对话模型已被广泛采用，但它们尚未展现出与人类自然聊天的能力。在本研究中，我们将用户话语视为原因，将生成的回复视为结果，并认识到原因的变化应产生不同的结果。为了进一步探索这一概念，我们通过众包方式编制并扩展了一个名为 CausalDialogue 的新数据集。该数据集在有向无环图（DAG）结构中包含多个因果对。我们的分析表明，传统损失函数难以有效融入 DAG 结构，因此我们提出了一种因果增强方法，称为指数最大平均处理效应（ExMATE），以在训练神经对话模型时增强话语层面的因果影响。为了评估在对话生成中考虑因果关系的必要性，我们使用不同的模型、推理方法和训练方法，在 CausalDialogue 数据集上构建了一个全面的基准。通过实验，我们发现像 ExMATE 这样受因果启发的损失函数能够提高传统损失函数的多样性和敏捷性，并且在该新数据集上要达到人类水平的质量仍有改进空间。
英文摘要：
Despite their widespread adoption, neural conversation models have yet to exhibit natural chat capabilities with humans. In this research, we examine user utterances as causes and generated responses as effects, recognizing that changes in a cause should produce a different effect. To further explore this concept, we have compiled and expanded upon a new dataset called CausalDialogue through crowd-sourcing. This dataset includes multiple cause-effect pairs within a directed acyclic graph (DAG) structure. Our analysis reveals that traditional loss functions struggle to effectively incorporate the DAG structure, leading us to propose a causality-enhanced method called Exponential Maximum Average Treatment Effect (ExMATE) to enhance the impact of causality at the utterance level in training neural conversation models. To evaluate the needs of considering causality in dialogue generation, we built a comprehensive benchmark on CausalDialogue dataset using different models, inference, and training methods. Through experiments, we find that a causality-inspired loss like ExMATE can improve the diversity and agility of conventional loss function and there is still room for improvement to reach human-level quality on this new dataset.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
