No project description provided
Project description
MWPToolkit
MWPToolkit is a PyTorch-based toolkit for Math Word Problem(MWP) solving. It is a comprehensive framework for research purpose that integrates popular MWP benchmark datasets and typical deep learning-based MWP algorithms.
Feature
- Comprehensive toolkit for MWP solving task. To our best knowledge, MWP toolkit is the first open-source library for MWP solving task, where popular benchmark datasets and advanced deep learning-based methods for MWP solving tasks are integrated into a unified framework.
- Easy to get started. MWP toolkit is developed upon Python and Pytorch. We provide detailed instruction, which facilitates users to evaluate the build-in datasets or apply the code to their own data.
- Highly modularized framework. MWP toolkit is designed with highly reused modules and provides convenient interfaces for users. Specifically, data preprocessor, data loader, encoder, decoder and evaluator form the running procedure. Each module could be developed and extended independently.
News
- Fix some bugs.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
mwptoolkit-0.0.5.tar.gz
(245.7 kB
view hashes)
Built Distribution
mwptoolkit-0.0.5-py3-none-any.whl
(341.6 kB
view hashes)
Close
Hashes for mwptoolkit-0.0.5-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 415614cbf26c9b57d52a87559c75d4caa75b74b1d2f0938d4471292005660293 |
|
MD5 | 0d1e0f29e4a729155030868b01bef5de |
|
BLAKE2b-256 | 1cd87471d7417f8f997b13783b9e3eed0494533a22f34963ff1a7b294d6488a3 |