Conversational Neuro-Symbolic Commonsense Reasoning

By Forough Arabshahi, Jennifer Lee, Mikayla Gawarecki, Kathryn Mazaitis, Amos Azaria, Tom Michael Mitchell. 2020

54 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Prompting & Reasoning, Dialogue & Conversational AI, Knowledge Graphs & Representation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Prompting & Reasoning

In Dialogue & Conversational AI

In Knowledge Graphs & Representation

Citations in the corpus

Natural Language Deduction through Search over Statement Compositions (2022, methodology): “Similar backward search ideas were used in Arabshahi et al. (2021).”
Think Before You Speak: Using Self-talk to Generate Implicit Commonsense Knowledge for Response Generation (2021, background): “Arabshahi et al. (2020) focuses on if-then-because reasoning in conversations and design a theorem prover.”
Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules (2021, methodology): “Our approach addresses a new reasoning task proposed by Arabshahi et al. (2021) that contains commands given to an instructable agent satisfying a general template.”
Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Text (2021, background): “ration from neuro-symbolic reasoning (Wang et al., 2018; Arabshahi et al., 2020) to integrate symbolic inference and neural representation.”