Characterizing Neuro-Symbolic Reasoning in NLP
Published in SUKI: Structured and Unstructured Knowledge Integration, Workshop at NAACL 2022, 2022
Neuro-symbolic reasoning has recently seen a revival as a promising way to bridge the gap between deep learning models that manipulate continuous spaces and the symbolic representations. Despite its promise, the term “neurosymbolic” remains nebulous and is used in various contexts, from systems that rely on having a rule-based sub-component to systems trained end-to-end using techniques like reinforcement learning. In this work, we conduct a survey of its various interpretations amongst researchers in the natural language processing (NLP) community along with a survey of prior work that focuses on neuro-symbolic methods.