A review of the literature on neuro-symbolic methods for natural language processing.
What is it about?
We conduct a structured review of studies implementing NeSy for NLP aiming to answer whether NeSy is meeting its promises: reasoning, out-of-distribution generalization, interpretability, learning and reasoning from small data, and transferability to new domains. We examine the impact of knowledge representation, such as rules and semantic networks, language structure and relational structure, and whether implicit or explicit reasoning contributes to higher promise scores.
Why is it important?
We find many discrepancies in how reasoning is defined, specifically in relation to human-level reasoning, which impacts decisions about model architectures and drives conclusions which are not always consistent across studies. Hence, we advocate for a more methodical approach to the application of theories of human reasoning as well as the development of appropriate benchmarks, which we hope can lead to a better understanding of progress in the field.