Neuro-symbolic Commonsense Social Reasoning
This addresses the problem of AI systems reasoning about social situations, though it appears incremental as it builds on existing datasets and methods.
The paper tackles the challenge of formalizing and reasoning with social norms by developing a neuro-symbolic system that converts natural language social rules into first-order logic and uses a theorem prover for reasoning, achieving robust handling of different text wordings and incorrect parses.
Social norms underlie all human social interactions, yet formalizing and reasoning with them remains a major challenge for AI systems. We present a novel system for taking social rules of thumb (ROTs) in natural language from the Social Chemistry 101 dataset and converting them to first-order logic where reasoning is performed using a neuro-symbolic theorem prover. We accomplish this in several steps. First, ROTs are converted into Abstract Meaning Representation (AMR), which is a graphical representation of the concepts in a sentence, and align the AMR with RoBERTa embeddings. We then generate alternate simplified versions of the AMR via a novel algorithm, recombining and merging embeddings for added robustness against different wordings of text, and incorrect AMR parses. The AMR is then converted into first-order logic, and is queried with a neuro-symbolic theorem prover. The goal of this paper is to develop and evaluate a neuro-symbolic method which performs explicit reasoning about social situations in a logical form.