面向任务的对话反应生成的回顾和前瞻混合生成器
Retrospective and Prospective Mixture-of-Generators for Task-oriented Dialogue Response Generation
摘要：
对话应答生成是面向任务的对话系统的一个重要组成部分。其目的是在给定某些上下文的情况下生成适当的自然语言响应，例如，历史话语、系统状态等。最先进的工作集中在如何以端到端的方式更好地处理DRG。通常，这样的研究假设每个标记都来自输出词汇表上的单个分布，这可能并不总是最佳的。不同意图的反应差异很大，例如，域、系统操作。我们提出了一种新的混合发电机网络（MoGNet）的DRG，我们假设每个令牌的响应是从混合分布。MoGNet由一个椅子生成器和几个专家生成器组成。每个专家都专门负责DRG w.r.t.一个特定的意图。主席协调多位专家，并结合他们产生的产出，以产生更适当的反应。我们提出了两种策略，以帮助主席作出更好的决策，即，一个回顾性的混合发电机（RMoG）和前瞻性的混合发电机（PMoG）。前者只考虑到历史专家生成的响应，直到当前的时间步，而后者也考虑可能的专家生成的响应，在未来的鼓励探索。为了区分专家，我们还设计了一个全球和本地（GL）的学习计划，迫使每个专家专门针对一个特定的意图使用本地损失和培训主席和所有专家协调使用全球损失。我们在MultiWOZ基准数据集上进行了广泛的实验。MoGNet在自动和人工评估方面都明显优于最先进的方法，证明了其对DRG的有效性。
英文摘要：
Dialogue response generation (DRG) is a critical component of task-oriented dialogue systems (TDSs). Its purpose is to generate proper natural language responses given some context, e.g., historical utterances, system states, etc. State-of-the-art work focuses on how to better tackle DRG in an end-to-end way. Typically, such studies assume that each token is drawn from a single distribution over the output vocabulary, which may not always be optimal. Responses vary greatly with different intents, e.g., domains, system actions. We propose a novel mixture-of-generators network (MoGNet) for DRG, where we assume that each token of a response is drawn from a mixture of distributions. MoGNet consists of a chair generator and several expert generators. Each expert is specialized for DRG w.r.t. a particular intent. The chair coordinates multiple experts and combines the output they have generated to produce more appropriate responses. We propose two strategies to help the chair make better decisions, namely, a retrospective mixture-of-generators (RMoG) and prospective mixture-of-generators (PMoG). The former only considers the historical expert-generated responses until the current time step while the latter also considers possible expert-generated responses in the future by encouraging exploration. In order to differentiate experts, we also devise a global-and-local (GL) learning scheme that forces each expert to be specialized towards a particular intent using a local loss and trains the chair and all experts to coordinate using a global loss. We carry out extensive experiments on the MultiWOZ benchmark dataset. MoGNet significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations, demonstrating its effectiveness for DRG.
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。
