Lune

EMNLP Findings2022

A Neural-Symbolic Approach to Natural Language Understanding

Zhixuan Liu, Zihao Wang, Yuan Lin, Hang Li

Abstract

Deep neural networks, empowered by pretrained language models, have achieved remarkable results in natural language understanding (NLU) tasks. However, their performances can drastically deteriorate when logical reasoning is needed. This is because NLU in principle depends on not only analogical reasoning, which deep neural networks are good at, but also logical reasoning. According to the dual-process theory, analogical reasoning and logical reasoning are respectively carried out by System 1 and System 2 in the human brain. Inspired by the theory, we present a novel framework for NLU called Neural-Symbolic Processor (NSP), which performs analogical reasoning based on neural processing and logical reasoning based on both neural and symbolic processing. As a case study, we conduct experiments on two NLU tasks, question answering (QA) and natural language inference (NLI), when numerical reasoning (a type of logical reasoning) is necessary. The experimental results show that our method significantly outperforms state-of-theart methods in both tasks. 1

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Question Directed Graph Attention Network for Numerical Reasoning over Text cites Neural Module Networks for Reasoning over Text
  • Question Directed Graph Attention Network for Numerical Reasoning over Text cites Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading Comprehension
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. Planning Like Human: A Dual-process Framework for Dialogue PlanningTao He, Lizi Liao, Yixin Cao, Yuanxing Liu et al.ACL 2024 · 7 citations
  2. A Neural Divide-and-Conquer Reasoning Framework for Image Retrieval from Linguistically Complex TextYunxin Li, Baotian Hu, Yuxin Ding, Lin Ma et al.ACL 2023 · 4 citations

Builds on5

  1. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
  2. Neural Module Networks for Reasoning over TextNitish Gupta, Kevin Lin, Dan Roth, Sameer Singh et al.ICLR 2020 · 134 citations
  3. Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading ComprehensionXinyun Chen, Chen Liang, Adams Wei Yu, Denny Zhou et al.ICLR 2020 · 109 citations
  4. Question Directed Graph Attention Network for Numerical Reasoning over TextKunlong Chen, Weidi Xu, Xingyi Cheng, Zou Xiaochuan et al.EMNLP 2020 · 48 citations
  5. ConjNLI: Natural Language Inference Over Conjunctive SentencesSwarnadeep Saha, Yixin Nie, Mohit BansalEMNLP 2020 · 1 citation

Related papers

  1. System 1 + System 2 = Better World: Neural-Symbolic Chain of Logic ReasoningWenyue Hua, Yongfeng ZhangEMNLP Findings 2022 · 10 citations
  2. LogicSAGE: Neuro-Symbolic Reasoning with Socratic-Guided EnhancementJinlong Tian, Jiang Yu, Kewei Cheng, Fengxiang Cheng et al.ICML 2026
  3. NeSTR: A Neuro-Symbolic Abductive Framework for Temporal Reasoning in Large Language ModelsFeng Liang, Weixin Zeng, Runhao Zhao, Xiang ZhaoAAAI 2026
  4. Weakly Supervised Neural Symbolic Learning for Cognitive TasksJidong Tian, Yitian Li, Wenqing Chen, Liqiang Xiao et al.AAAI 2022 · 14 citations
  5. Improved Logical Reasoning of Language Models via Differentiable Symbolic ProgrammingHanlin Zhang, Jiani Huang, Ziyang Li, Mayur Naik et al.ACL Findings 2023 · 17 citations
Dusk over the sea between two cliffs drawn in fine vertical lines