Work

Natural Language Reasoning, A Survey

Year: 2024

Type: article

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

Source: ACM Computing Surveys

DOI: 10.1145/3664194

Authors: Fei Yu, Hongbo Zhang, Prayag Tiwari, Benyou Wang

Institutions: Chinese University of Hong Kong, Shenzhen, Shenzhen Research Institute of Big Data, Halmstad University

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Shenzhen Science and Technology Innovation Program

OpenAlex ID: W4396762144

FWCI: 8.296

Cites: 132

Cited by: 61

Related to: 10