mlsanityData to 14 Oct 2026

Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems

arXiv 1811.00720 ↗First posted 2 Nov 2018cs.CLcited by 49

Not on the map. Why?

Abstract (arXiv)

Solving math word problems is a challenging task that requires accurate natural language understanding to bridge natural language texts and math expressions. Motivated by the intuition about how human generates the equations given the problem texts, this paper presents a neural approach to automatically solve math word problems by operating symbols according to their semantic meanings in texts. This paper views the process of generating equation as a bridge between the semantic world and the symbolic world, where the proposed neural math solver is based on an encoder-decoder framework. In the proposed model, the encoder is designed to understand the semantics of problems, and the decoder focuses on tracking semantic meanings of the generated symbols and then deciding which symbol to generate next. The preliminary experiments are conducted in a dataset Math23K, and our model significantly outperforms both the state-of-the-art single model and the best non-retrieval-based model over about 10% accuracy, demonstrating the effectiveness of bridging the symbolic and semantic worlds from math word problems.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 10; 2022: 19; 2023: 7; 2024: 8; 2025: 3; 2026: 2.

49 papers.

Sort:

By area:

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2023Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Stepcited by 148
  4. 2024Multi-Step Reasoning with Large Language Models, a Surveycited by 143
  5. 2022A Survey of Deep Learning for Mathematical Reasoningcited by 124
  6. 2022Teaching Algorithmic Reasoning via In-context Learningcited by 112
  7. 2021Generate & Rank: A Multi-task Framework for Math Word Problemscited by 82
  8. 2022Towards Complex Document Understanding By Discrete Reasoningcited by 82
  9. 2022Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extractioncited by 44
  10. 2021MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solverscited by 39
  11. 2021Neural-Symbolic Solver for Math Word Problems with Auxiliary Taskscited by 38
  12. 2024LLM Harmony: Multi-Agent Communication for Problem Solvingcited by 35
37 more
  1. 2021MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solvingcited by 32
  2. 2021Math Word Problem Generation with Mathematical Consistency and Problem Context Constraintscited by 27
  3. 2022LogicSolver: Towards Interpretable Math Word Problem Solving with Logical Prompt-enhanced Learningcited by 24
  4. 2021Adversarial Examples for Evaluating Math Word Problem Solverscited by 20
  5. 2023Code Prompting: a Neural Symbolic Method for Complex Reasoning in Large Language Modelscited by 16
  6. 2024Enhancing Mathematical Reasoning in LLMs by Stepwise Correctioncited by 16
  7. 2021NumGPT: Improving Numeracy Ability of Generative Pre-trained Modelscited by 15
  8. 2022JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understandingcited by 15
  9. 2024SciDoc2Diagrammer-MAF: Towards Generation of Scientific Diagrams from Documents guided by Multi-Aspect Feedback Refinementcited by 15
  10. 2022ELASTIC: Numerical Reasoning with Adaptive Symbolic Compilercited by 14
  11. 2021Recall and Learn: A Memory-augmented Solver for Math Word Problemscited by 13
  12. 2022Multi-View Reasoning: Consistent Contrastive Learning for Math Word Problemcited by 13
  13. 2024cPAPERS: A Dataset of Situated and Multimodal Interactive Conversations in Scientific Paperscited by 11
  14. 2022Self-consistent Reasoning For Solving Math Word Problemscited by 10
  15. 2024Infer Human's Intentions Before Following Natural Language Instructionscited by 10
  16. 2022Practice Makes a Solver Perfect: Data Augmentation for Math Word Problem Solverscited by 9
  17. 2022Why are NLP Models Fumbling at Elementary Math? A Survey of Deep Learning based Word Problem Solverscited by 9
  18. 2022Generalizing Math Word Problem Solvers via Solution Diversificationcited by 7
  19. 2022Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP Systemscited by 6
  20. 2022Semantic-based Data Augmentation for Math Word Problemscited by 5
  21. 2023Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphscited by 5
  22. 2022Structure-Unified M-Tree Coding Solver for MathWord Problemcited by 4
  23. 2023An Expression Tree Decoding Strategy for Mathematical Equation Generationcited by 4
  24. 2023Expression Syntax Information Bottleneck for Math Word Problemscited by 4
  25. 2022Improving Compositional Generalization in Math Word Problem Solvingcited by 3
  26. 2023In-Context Ability Transfer for Question Decomposition in Complex QAcited by 3
  27. 2024Survey of Natural Language Processing for Education: Taxonomy, Systematic Review, and Future Trendscited by 3
  28. 2025Empowering Bengali Education with AI: Solving Bengali Math Word Problems through Transformer Modelscited by 3
  29. 2023JiuZhang 2.0: A Unified Chinese Pre-trained Language Model for Multi-task Mathematical Problem Solvingcited by 2
  30. 2021WARM: A Weakly (+Semi) Supervised Model for Solving Math word Problemscited by 1
  31. 2026Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discoverycited by 1
  32. 2022Tackling Math Word Problems with Fine-to-Coarse Abstracting and Reasoningcited by 0
  33. 2022Heterogeneous Line Graph Transformer for Math Word Problemscited by 0
  34. 2024Data Augmentation with In-Context Learning and Comparative Evaluation in Math Word Problem Solvingcited by 0
  35. 2025Teaching Large Language Models Number-Focused Headline Generation With Key Element Rationalescited by 0
  36. 2025Rethinking Reasoning in LLMs: Neuro-Symbolic Local RetoMaton Beyond ICL and CoTcited by 0
  37. 2026SciText2Eq: Assessing LLMs for Explainable Equation Generation for Scientific Creativitycited by 0