arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.14725cs.CL
收藏

自然语言推理:综述

Natural Language Reasoning, A Survey

The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Halmstad University(哈尔姆斯塔德大学)

Fei Yu, Hongbo Zhang, Prayag Tiwari, Benyou Wang

AI总结:

本综述为NLP中的自然语言推理提供清晰定义与分类,全面回顾经典逻辑推理、自然语言推断、多跳问答和常识推理,并强调反向推理与可废止推理作为未来方向。

摘要:

本综述论文在概念和实践上为自然语言处理(NLP)领域中的自然语言推理提供了更清晰的视角。在概念上,我们基于哲学和NLP场景,为NLP中的自然语言推理给出了明确的定义,讨论了哪些类型的任务需要推理,并引入了推理的分类体系。在实践上,我们对NLP中的自然语言推理进行了全面的文献综述,主要涵盖经典逻辑推理、自然语言推断、多跳问答和常识推理。本文还识别并审视了反向推理——一种用于多步推理的强大范式,并将可废止推理作为自然语言推理研究中最重要的未来方向之一加以介绍。我们专注于单模态非结构化自然语言文本,不包括神经符号技术和数学推理。

英文摘要:

This survey paper proposes a clearer view of natural language reasoning in the field of Natural Language Processing (NLP), both conceptually and practically. Conceptually, we provide a distinct definition for natural language reasoning 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 natural language reasoning in NLP, mainly covering classical logical reasoning, natural language inference, multi-hop question answering, and commonsense reasoning. The paper 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 natural language reasoning research. We focus on single-modality unstructured natural language text, excluding neuro-symbolic techniques and mathematical reasoning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑