GithubHelp home page GithubHelp logo

graph2tree's Introduction

Graph-to-Tree Learning for Solving Math Word Problems

PyTorch implementation of Graph based Math Word Problem solver described in our ACL 2020 paper Graph-to-Tree Learning for Solving Math Word Problems. In this work, we propose a solution for Math Word Problem Solving via graph neural network.

Steps to run the experiments

Requirements

  • Python 3.6
  • >= PyTorch 1.0.0

For more details, please refer to requiremnt file.

Training

[MATH23K]

first get into the math23k directory:

  • cd math23k

training-test setting :

  • python run_seq2tree_graph.py

cross-validation setting :

  • python cross_valid_graph2tree.py

[MAWPS]

cross-validation setting :

  • cd mawps
  • python cross_valid_mawps.py

Contact

  • As I have graduated from my master school, my school email address will be invalid soon. If you have further questions about our work, you can refer to my new email address [email protected].

Reference

@article{zhang2020graph2tree,
  title={Graph-to-Tree Learning for Solving Math Word Problems},
  author={Zhang, Jipeng and Wang, Lei and Lee, Roy Ka-Wei and Bin, Yi and Shao, Jie and Lim, Ee-Peng},
  journal={ACL 2020},
  year={2020}
}

graph2tree's People

Contributors

2003pro avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

graph2tree's Issues

I have an error and would like to know how to remedy it.

Hello.
I am a university student studying artificial intelligence.
I am studying with your code as a reference.
I got an error in the last code "encoder_outputs, problem_output = encoder(input_var, input_length)" of the 59th execution of the published "seq2tree_analysis.ipynb" code.
The error code appears as "forward() missing 1 required positional argument: 'batch_graph'".
I would be happy to hear if there is any improvement.

MAWPS dataset

Hi Jipeng,

Where can we find the MAWPS dataset used for the evaluation? What is the original download link?

Thanks!

pytorch version

Can you tell me about program env ,such as pytorch version?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.