Task-oriented dialog (TOD) systems often require interaction with an external knowledge base to retrieve necessary entity (e.g., restaurant) information to support the response generation. Most current end-to-end TOD systems either retrieve the KB information explicitly or embed it into model parameters for implicit access.~While the former approach demands scanning the KB at each turn of response generation, which is inefficient when the KB scales up, the latter approach shows higher flexibility and efficiency. In either approach, the systems may generate a response with conflicting entity information. To address this issue, we propose to generate the entity autoregressively first and leverage it to guide the response generation in an end-to-end system. To ensure entity consistency, we impose a trie constraint on entity generation. We also introduce a logit concatenation strategy to facilitate gradient backpropagation for end-to-end training. Experiments on MultiWOZ 2.1 single and CAMREST show that our system can generate more high-quality and entity-consistent responses.
翻译:以任务为导向的对话(TOD)系统往往需要与外部知识库互动,以检索必要的实体(例如餐馆)信息,支持应急生成。目前大多数端到端的TOD系统要么明确检索KB信息,要么将其嵌入隐含访问的模型参数。~尽管前一种方法要求在每个响应生成的转弯都扫描KB,而当KB升级时,后者效率低下,但后者表现出更高的灵活性和效率。在这两种方法中,系统都可能产生与实体信息冲突的回应。为了解决这一问题,我们提议首先自动生成实体,并利用其在端到端系统中指导应急生成。为了确保实体的一致性,我们对实体生成实行三角制约。我们还引入了对齐策略,为端培训提供梯度回溯调整。关于多WOZ 2.1和CAMREST的实验表明,我们的系统可以产生更高质量和实体一致的响应。