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

@inproceedings{Chiang2019SemanticallyAlignedEG,
  title={Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems},
  author={Ting-Rui Chiang and Yun-Nung Chen},
  booktitle={NAACL-HLT},
  year={2019}
}
  • Ting-Rui Chiang, Yun-Nung Chen
  • Published in NAACL-HLT 2019
  • Computer Science
  • 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… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems
    Tree-structured Decoding for Solving Math Word Problems
    • 4
    • PDF
    The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers
    • 13
    • PDF
    Graph-to-Tree Learning for Solving Math Word Problems
    • 1
    • PDF
    Ape210K: A Large-Scale and Template-Rich Dataset of Math Word Problems
    An Improved Coarse-to-Fine Method for Solving Generation Tasks
    • 1
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 29 REFERENCES
    Mapping to Declarative Knowledge for Word Problem Solving
    • 17
    • PDF
    Equation Parsing : Mapping Sentences to Grounded Equations
    • 15
    • Highly Influential
    • PDF
    Solving Arithmetic Mathematical Word Problems: A Review and Recent Advancements
    • 5
    Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems
    • 79
    • PDF
    Reasoning about Quantities in Natural Language
    • 61
    • Highly Influential
    MathDQN: Solving Arithmetic Word Problems via Deep Reinforcement Learning
    • 33
    • PDF
    Parsing Algebraic Word Problems into Equations
    • 72
    • Highly Influential
    • PDF
    Annotating Derivations: A New Evaluation Strategy and Dataset for Algebra Word Problems
    • 17
    • PDF
    Deep Neural Solver for Math Word Problems
    • 51
    • Highly Influential
    • PDF