mlsanityData to 14 Oct 2026

Translating a Math Word Problem to an Expression Tree

arXiv 1811.05632 ↗First posted 14 Nov 2018cs.CLcited by 57

Not on the map. Why?

Abstract (arXiv)

Sequence-to-sequence (SEQ2SEQ) models have been successfully applied to automatic math word problem solving. Despite its simplicity, a drawback still remains: a math word problem can be correctly solved by more than one equations. This non-deterministic transduction harms the performance of maximum likelihood estimation. In this paper, by considering the uniqueness of expression tree, we propose an equation normalization method to normalize the duplicated equations. Moreover, we analyze the performance of three popular SEQ2SEQ models on the math word problem solving. We find that each model has its own specialty in solving problems, consequently an ensemble model is then proposed to combine their advantages. Experiments on dataset Math23K show that the ensemble model with equation normalization significantly outperforms the previous state-of-the-art methods.

Key facts. Cited by 57 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 13; 2022: 18; 2023: 11; 2024: 8; 2025: 5; 2026: 2.

57 papers.

Sort:

By area:

  1. 2021Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoningcited by 383
  2. 2022Large Language Models are Better Reasoners with Self-Verificationcited by 307
  3. 2021GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoningcited by 228
  4. 2022A Survey of Deep Learning for Mathematical Reasoningcited by 124
  5. 2021Generate & Rank: A Multi-task Framework for Math Word Problemscited by 82
  6. 2022Towards Complex Document Understanding By Discrete Reasoningcited by 82
  7. 2021Logic-Driven Context Extension and Data Augmentation for Logical Reasoning of Textcited by 46
  8. 2021From LSAT: The Progress and Challenges of Complex Reasoningcited by 43
  9. 2021MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solverscited by 39
  10. 2021Neural-Symbolic Solver for Math Word Problems with Auxiliary Taskscited by 38
  11. 2022Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computingcited by 35
  12. 2021MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solvingcited by 32
38 more
  1. 2023Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generationcited by 29
  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. 2021Investigating Math Word Problems using Pretrained Multilingual Language Modelscited by 21
  5. 2023Can neural networks do arithmetic? A survey on the elementary numerical skills of state-of-the-art deep learning modelscited by 18
  6. 2023Interpretable Math Word Problem Solution Generation Via Step-by-step Planningcited by 17
  7. 2023MinT: Boosting Generalization in Mathematical Reasoning via Multi-View Fine-Tuningcited by 16
  8. 2023Using Large Language Model to Solve and Explain Physics Word Problems Approaching Human Levelcited by 16
  9. 2021NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Datasetcited by 14
  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. 2022Self-consistent Reasoning For Solving Math Word Problemscited by 10
  13. 2022Unbiased Math Word Problems Benchmark for Mitigating Solving Biascited by 8
  14. 2024From Blind Solvers to Logical Thinkers: Benchmarking LLMs' Logical Integrity on Faulty Mathematical Problemscited by 8
  15. 2025Leveraging Large Language Models for Bengali Math Word Problem Solving with Chain of Thought Reasoningcited by 8
  16. 2022Generalizing Math Word Problem Solvers via Solution Diversificationcited by 7
  17. 2023Math Word Problem Solving by Generating Linguistic Variants of Problem Statementscited by 7
  18. 2023Solving Math Word Problem with Problem Type Classificationcited by 6
  19. 2024Text2MDT: Extracting Medical Decision Trees from Medical Textscited by 6
  20. 2024COMET: "Cone of experience" enhanced large multimodal model for mathematical problem generationcited by 6
  21. 2022Semantic-based Data Augmentation for Math Word Problemscited by 5
  22. 2023Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents via Semantic-Oriented Hierarchical Graphscited by 5
  23. 2025Generating Pedagogically Meaningful Visuals for Math Word Problems: A New Benchmark and Analysis of Text-to-Image Modelscited by 5
  24. 2022Structure-Unified M-Tree Coding Solver for MathWord Problemcited by 4
  25. 2022Analogical Math Word Problems Solving with Enhanced Problem-Solution Associationcited by 4
  26. 2023An Expression Tree Decoding Strategy for Mathematical Equation Generationcited by 4
  27. 2023Expression Syntax Information Bottleneck for Math Word Problemscited by 4
  28. 2024Demonstration Notebook: Finding the Most Suited In-Context Learning Example from Interactionscited by 4
  29. 2022Improving Compositional Generalization in Math Word Problem Solvingcited by 3
  30. 2022Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problemscited by 3
  31. 2024Survey of Natural Language Processing for Education: Taxonomy, Systematic Review, and Future Trendscited by 3
  32. 2025Empowering Bengali Education with AI: Solving Bengali Math Word Problems through Transformer Modelscited by 3
  33. 2024From Large to Tiny: Distilling and Refining Mathematical Expertise for Math Word Problems with Weakly Supervisioncited by 2
  34. 2021WARM: A Weakly (+Semi) Supervised Model for Solving Math word Problemscited by 1
  35. 2022ComSearch: Equation Searching with Combinatorial Strategy for Solving Math Word Problems with Weak Supervisioncited by 1
  36. 2025Foundation of Intelligence: Review of Math Word Problems from Human Cognition Perspectivecited by 1
  37. 2026BEAGLE: Behavior-Enforced Agent for Grounded Learner Emulationcited by 1
  38. 2026Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discoverycited by 1

50 most cited of 57 All 57 (JSON)