Conversational Neuro-Symbolic Commonsense Reasoning

TL;DR

This paper introduces a neuro-symbolic approach for understanding implicit commonsense in natural language commands, releasing a benchmark dataset and developing an interactive system that elicits human knowledge to improve reasoning in conversational AI.

Contribution

It presents a novel neuro-symbolic theorem prover for commonsense reasoning, a new benchmark dataset, and an interactive framework for eliciting human knowledge to enhance AI understanding.

Findings

The neuro-symbolic system effectively extracts multi-hop reasoning chains.

The benchmark dataset enables evaluation of commonsense reasoning in conversational AI.

The interactive framework improves reasoning coverage by engaging humans.

Abstract

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.