Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision
Not on the map. Why?
Abstract (arXiv)
Harnessing the statistical power of neural networks to perform language understanding and symbolic reasoning is difficult, when it requires executing efficient discrete operations against a large knowledge-base. In this work, we introduce a Neural Symbolic Machine, which contains (a) a neural "programmer", i.e., a sequence-to-sequence model that maps language utterances to programs and utilizes a key-variable memory to handle compositionality (b) a symbolic "computer", i.e., a Lisp interpreter that performs program execution, and helps find good programs by pruning the search space. We apply REINFORCE to directly optimize the task reward of this structured prediction problem. To train with weak supervision and improve the stability of REINFORCE, we augment it with an iterative maximum-likelihood training process. NSM outperforms the state-of-the-art on the WebQuestionsSP dataset when trained from question-answer pairs only, without requiring any feature engineering or domain-specific knowledge.
Key facts. Cited by 101 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Oct 2016.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2018: 5; 2019: 0; 2020: 0; 2021: 39; 2022: 23; 2023: 21; 2024: 8; 2025: 3; 2026: 2.
101 papers.
Sort:
By area:
- 2023Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Modelscited by 325
- 2022Binding Language Models in Symbolic Languagescited by 224
- 2022ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answeringcited by 194
- 2018Self-Imitation Learningcited by 135
- 2021HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generationcited by 117
- 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
- 2021Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signalscited by 100
- 2022Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answeringcited by 93
- 2023On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligencecited by 88
- 2021RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answeringcited by 86
- 2021Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoningcited by 85
- 2021A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutionscited by 77
38 more
- 2024TrustAgent: Towards Safe and Trustworthy LLM-based Agentscited by 62
- 2021TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graphcited by 60
- 2022TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Basescited by 59
- 2018Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learningcited by 57
- 2022Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environmentscited by 57
- 2021Neuro-Symbolic Artificial Intelligence: Current Trendscited by 54
- 2021Complex Knowledge Base Question Answering: A Surveycited by 52
- 2023KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Basescited by 52
- 2021AR-LSAT: Investigating Analytical Reasoning of Textcited by 49
- 2022ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answeringcited by 48
- 2021AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industrycited by 44
- 2023Enhancing Few-shot Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategiescited by 44
- 2021From LSAT: The Progress and Challenges of Complex Reasoningcited by 43
- 2022Knowledge Graph Embedding: A Survey from the Perspective of Representation Spacescited by 41
- 2021A Survey on Neural-symbolic Learning Systemscited by 39
- 2021Neural-Symbolic Solver for Math Word Problems with Auxiliary Taskscited by 38
- 2022Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutionscited by 38
- 2021Program Transfer for Answering Complex Questions over Knowledge Basescited by 34
- 2022NeuPSL: Neural Probabilistic Soft Logiccited by 34
- 2022Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computingcited by 34
- 2023AD-AutoGPT: An Autonomous GPT for Alzheimer's Disease Infodemiologycited by 34
- 2018Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedbackcited by 32
- 2018Generative Adversarial Self-Imitation Learningcited by 25
- 2021Conversational Question Answering over Knowledge Graphs with Transformer and Graph Attention Networkscited by 24
- 2021Geographic Question Answering: Challenges, Uniqueness, Classification, and Future Directionscited by 24
- 2022Knowledge Base Question Answering: A Semantic Parsing Perspectivecited by 22
- 2021GNN is a Counter? Revisiting GNN for Question Answeringcited by 21
- 2023Exploring New Frontiers in Agricultural NLP: Investigating the Potential of Large Language Models for Food Applicationscited by 21
- 2021Reasoning Over Virtual Knowledge Bases With Open Predicate Relationscited by 18
- 2024Softened Symbol Grounding for Neuro-symbolic Systemscited by 16
- 2025SEDM: Scalable Self-Evolving Distributed Memory for Agentscited by 16
- 2022Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisationcited by 15
- 2021From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decodingcited by 14
- 2023API-Assisted Code Generation for Question Answering on Varied Table Structurescited by 14
- 2021On The Ingredients of an Effective Zero-shot Semantic Parsercited by 13
- 2021Multi-Row, Multi-Span Distant Supervision For Table+Text Questioncited by 12
- 2023Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answeringcited by 11
- 2023Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQAcited by 11
50 most cited of 101 All 101 (JSON)
- 2026GDPR Auto-Formalization with AI Agents and Human Verification16 Apr 2026
- 2026MDER-DR: Multi-Hop Question Answering with Entity-Centric Summaries11 Mar 2026
- 2025SEDM: Scalable Self-Evolving Distributed Memory for Agents11 Sep 2025
- 2025PanelTR: Zero-Shot Table Reasoning Framework Through Multi-Agent Scientific Discussion8 Aug 2025
- 2025Learning to Place Objects with Programs and Iterative Self Training6 Mar 2025
- 2024Bridging the Gap: Representation Spaces in Neuro-Symbolic AI7 Nov 2024
- 2024Neuro-Symbolic AI: Explainability, Challenges, and Future Trends7 Nov 2024
- 2024TabVer: Tabular Fact Verification with Natural Logic2 Nov 2024
- 2024Semantic Parsing with Candidate Expressions for Knowledge Base Question Answering1 Oct 2024
- 2024UniOQA: A Unified Framework for Knowledge Graph Question Answering with Large Language Models4 Jun 2024
- 2024Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale13 Mar 2024
- 2024Softened Symbol Grounding for Neuro-symbolic Systems1 Mar 2024
38 more
- 2024TrustAgent: Towards Safe and Trustworthy LLM-based Agents2 Feb 2024
- 2023Relation-Aware Question Answering for Heterogeneous Knowledge Graphs19 Dec 2023
- 2023Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models11 Dec 2023
- 2023Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA14 Nov 2023
- 2023API-Assisted Code Generation for Question Answering on Varied Table Structures23 Oct 2023
- 2023A Framework for Empowering Reinforcement Learning Agents with Causal Analysis: Enhancing Automated Cryptocurrency Trading14 Oct 2023
- 2023Augmenting Transformers with Recursively Composed Multi-grained Representations28 Sep 2023
- 2023Improving Unsupervised Visual Program Inference with Code Rewriting Families26 Sep 2023
- 2023Localize, Retrieve and Fuse: A Generalized Framework for Free-Form Question Answering over Tables20 Sep 2023
- 2023Weakly Supervised Reasoning by Neuro-Symbolic Approaches19 Sep 2023
- 2023Semantic Parsing in Limited Resource Conditions14 Sep 2023
- 2023The Emergence of Chunking Structures with Hierarchical RNN10 Sep 2023
- 2023KnowledGPT: Enhancing Large Language Models with Retrieval and Storage Access on Knowledge Bases17 Aug 2023
- 2023Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systems14 Jul 2023
- 2023VisKoP: Visual Knowledge oriented Programming for Interactive Knowledge Base Question Answering6 Jul 2023
- 2023Exploring New Frontiers in Agricultural NLP: Investigating the Potential of Large Language Models for Food Applications20 Jun 2023
- 2023AD-AutoGPT: An Autonomous GPT for Alzheimer's Disease Infodemiology16 Jun 2023
- 2023History Semantic Graph Enhanced Conversational KBQA with Temporal Information Modeling12 Jun 2023
- 2023Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering24 May 2023
- 2023Enhancing Few-shot Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategies21 May 2023
- 2023On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence13 Apr 2023
- 2023AGI for Agriculture12 Apr 2023
- 2022Optimization Techniques for Unsupervised Complex Table Reasoning via Self-Training Framework20 Dec 2022
- 2022Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments19 Dec 2022
- 2022Explicit Knowledge Transfer for Weakly-Supervised Code Generation30 Nov 2022
- 2022Differentiable Fuzzy ALC: A Neural-Symbolic Representation Language for Symbol Grounding22 Nov 2022
- 2022Knowledge Graph Embedding: A Survey from the Perspective of Representation Spaces7 Nov 2022
- 2022Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing28 Oct 2022
- 2022TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Bases24 Oct 2022
- 2022ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering7 Oct 2022
- 2022Binding Language Models in Symbolic Languages6 Oct 2022
- 2022Knowledge Base Question Answering: A Semantic Parsing Perspective12 Sep 2022
- 2022Knowledge-enhanced Iterative Instruction Generation and Reasoning for Knowledge Base Question Answering7 Sep 2022
- 2022Neuro-Symbolic Learning: Principles and Applications in Ophthalmology31 Jul 2022
- 2022Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisation28 Jul 2022
- 2022Discourse-Aware Graph Networks for Textual Logical Reasoning4 Jul 2022
- 2022Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions28 May 2022
- 2022NeuPSL: Neural Probabilistic Soft Logic27 May 2022
50 newest of 101 All 101 (JSON)
- 2022ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answeringcited by 194
- 2021HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generationcited by 117
- 2022Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutionscited by 38
- 2022NeuPSL: Neural Probabilistic Soft Logiccited by 34
- 2022Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisationcited by 15
- 2024TabVer: Tabular Fact Verification with Natural Logiccited by 3
- 2022Discourse-Aware Graph Networks for Textual Logical Reasoningcited by 2
- 2022Differentiable Fuzzy ALC: A Neural-Symbolic Representation Language for Symbol Groundingcited by 1
- 2025PanelTR: Zero-Shot Table Reasoning Framework Through Multi-Agent Scientific Discussioncited by 1
- 2025PanelTR: Zero-Shot Table Reasoning Framework Through Multi-Agent Scientific Discussion8 Aug 2025
- 2024TabVer: Tabular Fact Verification with Natural Logic2 Nov 2024
- 2022Differentiable Fuzzy ALC: A Neural-Symbolic Representation Language for Symbol Grounding22 Nov 2022
- 2022ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering7 Oct 2022
- 2022Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisation28 Jul 2022
- 2022Discourse-Aware Graph Networks for Textual Logical Reasoning4 Jul 2022
- 2022Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions28 May 2022
- 2022NeuPSL: Neural Probabilistic Soft Logic27 May 2022
- 2021HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation15 Aug 2021
- 2018Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learningcited by 57
- 2018Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedbackcited by 32
- 2018Counterfactual Learning from Human Proofreading Feedback for Semantic Parsingcited by 4
- 2018Counterfactual Learning from Human Proofreading Feedback for Semantic Parsing29 Nov 2018
- 2018Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning27 May 2018
- 2018Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback3 May 2018
- 2018Self-Imitation Learningcited by 135
- 2018Generative Adversarial Self-Imitation Learningcited by 25
- 2018Generative Adversarial Self-Imitation Learning3 Dec 2018
- 2018Self-Imitation Learning14 Jun 2018
- 2022Binding Language Models in Symbolic Languagescited by 224
- 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
- 2021Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signalscited by 100
- 2022Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answeringcited by 93
- 2023On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligencecited by 88
- 2021RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answeringcited by 86
- 2021Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoningcited by 85
- 2021A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutionscited by 77
- 2021TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graphcited by 60
- 2022TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Basescited by 59
- 2022Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environmentscited by 57
- 2021Neuro-Symbolic Artificial Intelligence: Current Trendscited by 54
12 most cited of 82 All 82 (JSON)
- 2025SEDM: Scalable Self-Evolving Distributed Memory for Agents11 Sep 2025
- 2025Learning to Place Objects with Programs and Iterative Self Training6 Mar 2025
- 2024Bridging the Gap: Representation Spaces in Neuro-Symbolic AI7 Nov 2024
- 2024Neuro-Symbolic AI: Explainability, Challenges, and Future Trends7 Nov 2024
- 2024Semantic Parsing with Candidate Expressions for Knowledge Base Question Answering1 Oct 2024
- 2024UniOQA: A Unified Framework for Knowledge Graph Question Answering with Large Language Models4 Jun 2024
- 2024Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale13 Mar 2024
- 2024Softened Symbol Grounding for Neuro-symbolic Systems1 Mar 2024
- 2023Relation-Aware Question Answering for Heterogeneous Knowledge Graphs19 Dec 2023
- 2023Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA14 Nov 2023
- 2023API-Assisted Code Generation for Question Answering on Varied Table Structures23 Oct 2023
- 2023A Framework for Empowering Reinforcement Learning Agents with Causal Analysis: Enhancing Automated Cryptocurrency Trading14 Oct 2023
12 newest of 82 All 82 (JSON)