arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2111.00570cs.CLcs.AI
收藏

一种推理驱动的社交聊天机器人对话管理方法

An Approach to Inference-Driven Dialogue Management within a Social Chatbot

Emory University(埃默里大学)

Sarah E. Finch, James D. Finch, Daniil Huryn, William Hutsell, Xiaoyuan Huang, Han He, Jinho D. Choi

摘要:

我们提出了一个聊天机器人实现一种新的对话管理方法的基础上逻辑推理。我们没有将对话框定为一系列响应生成任务,而是将对话建模为一个协作推理过程,在这个过程中,说话者共享信息以实时的合成新知识。我们的聊天机器人管道在三个主要阶段完成了这个建模。第一阶段将用户话语翻译成符号谓词表示。然后,第二阶段使用这种结构化表示结合更大的知识库,使用高效的图匹配来合成新的谓词。在第三个也是最后一个阶段,我们的机器人选择一小部分谓词,并将它们翻译成英语响应。这种方法有助于理解用户输入的潜在语义,灵活的主动性,以及与对话上下文新颖且一致的响应。

英文摘要:

We present a chatbot implementing a novel dialogue management approach based on logical inference. Instead of framing conversation a sequence of response generation tasks, we model conversation as a collaborative inference process in which speakers share information to synthesize new knowledge in real time. Our chatbot pipeline accomplishes this modelling in three broad stages. The first stage translates user utterances into a symbolic predicate representation. The second stage then uses this structured representation in conjunction with a larger knowledge base to synthesize new predicates using efficient graph matching. In the third and final stage, our bot selects a small subset of predicates and translates them into an English response. This approach lends itself to understanding latent semantics of user inputs, flexible initiative taking, and responses that are novel and coherent with the dialogue context.

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。

↑