arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.08708cs.CL
收藏

面向端到端任务对话的自回归实体生成

Autoregressive Entity Generation for End-to-End Task-Oriented Dialog

School of Computer Science and Engineering(计算机科学与工程学院);Sun Yat-sen University(中山大学);Meta AI

Guanhuan Huang, Xiaojun Quan, Qifan Wang

摘要:

面向任务的对话(TOD)系统通常需要与外部知识库交互以检索必要的实体(例如,餐馆)信息以支持响应生成。大多数当前的端到端TOD系统要么显式地检索KB信息,要么将其嵌入到模型参数中以进行隐式访问。虽然前一种方法需要在响应生成的每一轮扫描KB,这在KB扩展时是低效的,但后一种方法显示出更高的灵活性和效率。在任一方法中,系统可以生成具有冲突实体信息的响应。为了解决这个问题,我们建议首先生成实体自回归,并利用它来指导端到端系统中的响应生成。为了保证实体的一致性,我们对实体的生成施加了一个trie约束。我们还引入了一个logit级联策略,以促进端到端训练的梯度反向传播。在MultiWOZ 2.1 single和CAMREST上的实验表明,该系统能够生成更高质量和实体一致性的响应。

英文摘要:

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.

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。

↑