通过序列后验推理实现多样且忠实于知识的对话生成
Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference
AI总结：
本文提出序列后验推理（SPI）框架，通过直接从后验分布近似采样联合优化知识选择与回复生成，无需推理网络或简单后验假设，并在两个对话数据集上取得优于强基线的自动与人工评估结果。
摘要：
利用事实知识生成具有多样性和忠实性的回复，对于构建类人且可信赖的对话系统至关重要。常见策略要么采用两阶段范式，分别优化知识选择和回复生成，可能忽视这两个任务之间的内在关联；要么利用条件变分方法，通过引入推理网络来联合优化知识选择和回复生成。本文提出一个端到端学习框架，称为序列后验推理（Sequential Posterior Inference，SPI），能够通过近似从后验分布中采样来选择知识并生成对话。与其他方法不同，SPI 不需要推理网络，也不假设后验分布具有简单的几何结构。SPI 这种直接且直观的推理过程直接查询回复生成模型，从而能够准确选择知识并生成忠实的回复。除了建模方面的贡献外，我们在两个常用对话数据集（Wizard of Wikipedia 和 Holl-E）上的实验结果表明，根据自动评估和人工评估指标，SPI 均优于此前较强的基线模型。
英文摘要：
The capability to generate responses with diversity and faithfulness using factual knowledge is paramount for creating a human-like, trustworthy dialogue system. Common strategies either adopt a two-step paradigm, which optimizes knowledge selection and response generation separately, and may overlook the inherent correlation between these two tasks, or leverage conditional variational method to jointly optimize knowledge selection and response generation by employing an inference network. In this paper, we present an end-to-end learning framework, termed Sequential Posterior Inference (SPI), capable of selecting knowledge and generating dialogues by approximately sampling from the posterior distribution. Unlike other methods, SPI does not require the inference network or assume a simple geometry of the posterior distribution. This straightforward and intuitive inference procedure of SPI directly queries the response generation model, allowing for accurate knowledge selection and generation of faithful responses. In addition to modeling contributions, our experimental results on two common dialogue datasets (Wizard of Wikipedia and Holl-E) demonstrate that SPI outperforms previous strong baselines according to both automatic and human evaluation metrics.
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。
