Learning from Explicit and Implicit Supervision Jointly For Algebra Word Problems

@inproceedings{Upadhyay2016LearningFE,
  title={Learning from Explicit and Implicit Supervision Jointly For Algebra Word Problems},
  author={Shyam Upadhyay and Ming-Wei Chang and Kai-Wei Chang and Wen-tau Yih},
  booktitle={EMNLP},
  year={2016}
}
  • Shyam Upadhyay, Ming-Wei Chang, +1 author Wen-tau Yih
  • Published in EMNLP 2016
  • Computer Science
  • Automatically solving algebra word problems has raised considerable interest recently. Existing state-of-the-art approaches mainly rely on learning from human annotated equations. In this paper, we demonstrate that it is possible to efficiently mine algebra problems and their numerical solutions with little to no manual effort. To leverage the mined dataset, we propose a novel structured-output learning algorithm that aims to learn from both explicit (e.g., equations) and implicit (e.g… CONTINUE READING
    24 Citations
    Using Intermediate Representations to Solve Math Word Problems
    • 7
    • PDF
    Maximum Margin Reward Networks for Learning from Explicit and Implicit Supervision
    • 15
    • PDF
    Mapping to Declarative Knowledge for Word Problem Solving
    • Subhro Roy, D. Roth
    • Computer Science
    • Transactions of the Association for Computational Linguistics
    • 2018
    • 18
    • PDF
    MathDQN: Solving Arithmetic Word Problems via Deep Reinforcement Learning
    • 34
    • PDF
    Learning Fine-Grained Expressions to Solve Math Word Problems
    • 29
    • Highly Influenced
    • PDF
    A Neural Semantic Parser for Math Problems Incorporating Multi-Sentence Information
    • 1
    The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers
    • 18
    • Highly Influenced
    • PDF
    Annotating Derivations: A New Evaluation Strategy and Dataset for Algebra Word Problems
    • 18
    • PDF
    Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems
    • 11
    • PDF
    Neural Math Word Problem Solver with Reinforcement Learning
    • 17

    References

    SHOWING 1-10 OF 34 REFERENCES
    Learning to Automatically Solve Algebra Word Problems
    • 181
    • Highly Influential
    • PDF
    How well do Computers Solve Math Word Problems? Large-Scale Dataset Construction and Evaluation
    • 39
    • PDF
    Learn to Solve Algebra Word Problems Using Quadratic Programming
    • 51
    • Highly Influential
    • PDF
    Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions
    • 352
    • PDF
    Annotating Derivations: A New Evaluation Strategy and Dataset for Algebra Word Problems
    • 18
    • PDF
    Semantic Parsing on Freebase from Question-Answer Pairs
    • 982
    • Highly Influential
    • PDF
    Parsing Algebraic Word Problems into Equations
    • 75
    • PDF
    Support vector machine learning for interdependent and structured output spaces
    • 1,416
    • PDF
    Solving General Arithmetic Word Problems
    • 88
    • PDF
    Learning with Relaxed Supervision
    • 6
    • PDF