Natural Language Reasoning, A Survey
Fei Yu, Hongbo Zhang, Prayag Tiwari, Benyou Wang
Abstract
This survey article proposes a clearer view of Natural Language Reasoning (NLR) in the field of Natural Language Processing (NLP) , both conceptually and practically. Conceptually, we provide a distinct definition for NLR in NLP, based on both philosophy and NLP scenarios; discuss what types of tasks require reasoning; and introduce a taxonomy of reasoning. Practically, we conduct a comprehensive literature review on NLR in NLP, mainly covering classical logical reasoning, Natural Language Inference (NLI) , multi-hop question answering, and commonsense reasoning. The article also identifies and views backward reasoning, a powerful paradigm for multi-step reasoning, and introduces defeasible reasoning as one of the most important future directions in NLR research. We focus on single-modality unstructured natural language text, excluding neuro-symbolic research and mathematical reasoning. 1