mlsanityData to 7 Oct 2026

Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving

arXiv 2106.00990 ↗First posted 2 Jun 2021cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

With the recent advancements in deep learning, neural solvers have gained promising results in solving math word problems. However, these SOTA solvers only generate binary expression trees that contain basic arithmetic operators and do not explicitly use the math formulas. As a result, the expression trees they produce are lengthy and uninterpretable because they need to use multiple operators and constants to represent one single formula. In this paper, we propose sequence-to-general tree (S2G) that learns to generate interpretable and executable operation trees where the nodes can be formulas with an arbitrary number of arguments. With nodes now allowed to be formulas, S2G can learn to incorporate mathematical domain knowledge into problem-solving, making the results more interpretable. Experiments show that S2G can achieve a better performance against strong baselines on problems that require domain knowledge.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 14 of its 41 references that are in the map. First posted on arXiv 2 Jun 2021.

Builds on

14 of 41 references.

References · 14

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Graph Attention Networkscited by 8,854
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  4. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  5. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  6. 2016Incorporating Copying Mechanism in Sequence-to-Sequence Learningcited by 217
  7. 2016Language to Logical Form with Neural Attentioncited by 158
  8. 2016Sequence-to-Sequence Learning as Beam-Search Optimizationcited by 126
  9. 2017Abstract Syntax Networks for Code Generation and Semantic Parsingcited by 92
  10. 2017Mapping to Declarative Knowledge for Word Problem Solvingcited by 36
  11. 2018The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solverscited by 31
  12. 2020Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problemcited by 31
2 more
  1. 2018A Meaning-based Statistical English Math Word Problem Solvercited by 10
  2. 2020Towards Question Format Independent Numerical Reasoning: A Set of Prerequisite Taskscited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 1; 2023: 3; 2024: 4; 2025: 1; 2026: 1.

11 papers.

  1. 2023A Multi-Modal Neural Geometric Solver with Textual Clauses Parsed from Diagramcited by 55
  2. 2024GeoEval: Benchmark for Evaluating LLMs and Multi-Modal Models on Geometry Problem-Solvingcited by 44
  3. 2023FormalGeo: An Extensible Formalized Framework for Olympiad Geometric Problem Solvingcited by 26
  4. 2021Solving Linear Algebra by Program Synthesiscited by 14
  5. 2024Fuse, Reason and Verify: Geometry Problem Solving with Parsed Clauses from Diagramcited by 13
  6. 2022Why are NLP Models Fumbling at Elementary Math? A Survey of Deep Learning based Word Problem Solverscited by 9
  7. 2024FGeo-HyperGNet: Geometric Problem Solving Integrating FormalGeo Symbolic System and Hypergraph Neural Networkcited by 7
  8. 2023An Expression Tree Decoding Strategy for Mathematical Equation Generationcited by 4
  9. 2025A Survey of Deep Learning for Geometry Problem Solvingcited by 4
  10. 2026GeoFocus: Blending Efficient Global-to-Local Perception for Multimodal Geometry Problem-Solvingcited by 1
  11. 2024A Theoretical Review on Solving Algebra Problemscited by 0