对话连贯性与基于响应的上下文重写用于多方对话生成
Discourse Coherence and Response-Guided Context Rewriting for Multi-Party Dialogue Generation
AI总结：
本文提出DRCR框架，通过对话上下文重写提升多方对话生成效果，利用对话连贯性和响应质量构建偏好数据，并采用动态自进化学习方法增强重写与响应能力。
摘要：
先前多方对话生成研究主要依赖对话内固有的结构信息直接指导生成过程。然而，对话中普遍存在的口语化表达和不完整陈述往往阻碍理解并削弱对话结构表示的准确性，特别是在多方对话中尤为明显。在本工作中，我们提出了一种新的框架DRCR（对话连贯性与基于响应的上下文重写），通过对话上下文重写来改进多方对话生成。具体而言，DRCR利用两种互补的反馈信号，即对话连贯性和响应质量，来构建用于上下文重写和响应生成的偏好数据。此外，我们提出了一种动态自进化学习方法，使重写器和响应器通过迭代训练循环中的相互作用持续提升能力。在四个多方对话数据集上的全面实验验证了DRCR的有效性。
英文摘要：
Previous research on multi-party dialogue generation has predominantly leveraged structural information inherent in dialogues to directly inform the generation process. However, the prevalence of colloquial expressions and incomplete utterances in dialogues often impedes comprehension and weakens the fidelity of dialogue structure representations, which is particularly pronounced in multi-party dialogues. In this work, we propose a novel framework DRCR (Discourse coherence and Response-guided Context Rewriting) to improve multi-party dialogue generation through dialogue context rewriting. Specifically, DRCR employs two complementary feedback signals, discourse coherence and response quality, to construct preference data for both context rewriting and response generation. Moreover, we propose a dynamic self-evolution learning method that allows the rewriter and responder to continuously enhance their capabilities through mutual interaction in an iterative training loop. Comprehensive experiments conducted on four multi-party dialogue datasets substantiate the effectiveness of DRCR.
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。
