We introduce AARGH, an end-to-end task-oriented dialog system combining retrieval and generative approaches in a single model, aiming at improving dialog management and lexical diversity of outputs. The model features a new response selection method based on an action-aware training objective and a simplified single-encoder retrieval architecture which allow us to build an end-to-end retrieval-enhanced generation model where retrieval and generation share most of the parameters. On the MultiWOZ dataset, we show that our approach produces more diverse outputs while maintaining or improving state tracking and context-to-response generation performance, compared to state-of-the-art baselines.
翻译:我们引入了AARGH,这是一个端到端以任务为导向的对话系统,将检索和基因化方法合并成一个单一模式,目的是改进对话管理和产出的词汇多样性,该模式以行动意识培训目标和简化的单编码检索结构为基础,采用新的响应选择方法,使我们能够建立一个端到端检索增强的生成模型,在其中,检索和生成的参数占大多数。关于多功能组织数据集,我们显示,我们的方法产生更多样化的产出,同时保持或改进国家跟踪和因应生成功能,与最先进的基线相比。