arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.10022cs.AIcs.CLcs.LGstat.ML
收藏

会话神经符号常识推理

Conversational Neuro-Symbolic Commonsense Reasoning

Carnegie Mellon University(卡内基梅隆大学)

Forough Arabshahi, Jennifer Lee, Mikayla Gawarecki, Kathryn Mazaitis, Amos Azaria, Tom Mitchell

摘要:

为了让对话式人工智能系统进行更自然、更广泛的对话,它们需要更多的常识,包括识别对话伙伴未陈述的假设的能力。例如,在命令“如果晚上下雪,那么早点叫醒我,因为我不想上班迟到”中,说话者依赖于听者的常识推理来推断出他们希望仅在雪下得足以导致交通减速时才被叫醒的隐含假设。我们在这里考虑的问题,理解这种不精确的陈述自然语言命令的形式给出的“如果-(状态),然后-(行动),因为-(目标)”语句。更准确地说,我们考虑的问题,确定未陈述的假设的发言者,允许请求的行动,以实现预期的目标,从给定的状态(也许详细说明,使隐式的假设明确)。我们为这项任务发布了一个基准数据集,从人类那里收集,并用常识假设进行了注释。我们提出了一个神经符号定理证明,提取多跳推理链,并将其应用到这个问题。此外,为了适应当前人工智能常识系统缺乏全面覆盖的现实,我们还提出了一个基于神经符号系统的交互式对话框架,该框架通过对话唤起人类的常识知识来完成其推理链。

英文摘要:

In order for conversational AI systems to hold more natural and broad-ranging conversations, they will require much more commonsense, including the ability to identify unstated presumptions of their conversational partners. For example, in the command "If it snows at night then wake me up early because I don't want to be late for work" the speaker relies on commonsense reasoning of the listener to infer the implicit presumption that they wish to be woken only if it snows enough to cause traffic slowdowns. We consider here the problem of understanding such imprecisely stated natural language commands given in the form of "if-(state), then-(action), because-(goal)" statements. More precisely, we consider the problem of identifying the unstated presumptions of the speaker that allow the requested action to achieve the desired goal from the given state (perhaps elaborated by making the implicit presumptions explicit). We release a benchmark data set for this task, collected from humans and annotated with commonsense presumptions. We present a neuro-symbolic theorem prover that extracts multi-hop reasoning chains, and apply it to this problem. Furthermore, to accommodate the reality that current AI commonsense systems lack full coverage, we also present an interactive conversational framework built on our neuro-symbolic system, that conversationally evokes commonsense knowledge from humans to complete its reasoning chains.

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。

↑