This is the offcial repo for the KDD-2023 paper "Guiding Mathematical Reasoning via Mastering Commonsense Formula Knowledge".
- python==3.6
- torch==1.7.1
- other pakages
- OS: CentOS Linux release 7.7.1908
- CPU: 64 Intel(R) Xeon(R) Gold 5218 CPU @ 2.30GHz
- GPU: Four Tesla V100-SXM2 32GB
- CUDA: 10.1
- Math23K-F
formula.txt: collection of 51 commonsense math formulas
formula_variant.txt: collection of 131 commonsense math formulas and their variants
- MAWPS-F
formula.txt: collection of 18 commonsense math formulas
formula_variant.txt: collection of 46 commonsense math formulas and their variants
For any question, please contact us with email: [email protected].
Train the model :
python run_seq2tree.py
If you find this work useful, please cite our paper:
@inproceedings{liu2023guiding,
title={Guiding Mathematical Reasoning via Mastering Commonsense Formula Knowledge},
author={Liu, Jiayu and Huang, Zhenya and Ma, Zhiyuan and Liu, Qi and Chen, Enhong and Su, Tianhuang and Liu, Haifeng},
booktitle={Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
pages={1477โ1488},
year={2023}
}