Improving Math Word Problems with Pre-trained Knowledge and Hierarchical Reasoning

Weijiang Yu, Yingpeng Wen, Fudan Zheng, Nong Xiao


Abstract
The recent algorithms for math word problems (MWP) neglect to use outside knowledge not present in the problems. Most of them only capture the word-level relationship and ignore to build hierarchical reasoning like the human being for mining the contextual structure between words and sentences. In this paper, we propose a Reasoning with Pre-trained Knowledge and Hierarchical Structure (RPKHS) network, which contains a pre-trained knowledge encoder and a hierarchical reasoning encoder. Firstly, our pre-trained knowledge encoder aims at reasoning the MWP by using outside knowledge from the pre-trained transformer-based models. Secondly, the hierarchical reasoning encoder is presented for seamlessly integrating the word-level and sentence-level reasoning to bridge the entity and context domain on MWP. Extensive experiments show that our RPKHS significantly outperforms state-of-the-art approaches on two large-scale commonly-used datasets, and boosts performance from 77.4% to 83.9% on Math23K, from 75.5 to 82.2% on Math23K with 5-fold cross-validation and from 83.7% to 89.8% on MAWPS. More extensive ablations are shown to demonstrate the effectiveness and interpretability of our proposed method.
Anthology ID:
2021.emnlp-main.272
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3384–3394
Language:
URL:
https://aclanthology.org/2021.emnlp-main.272
DOI:
10.18653/v1/2021.emnlp-main.272
Bibkey:
Cite (ACL):
Weijiang Yu, Yingpeng Wen, Fudan Zheng, and Nong Xiao. 2021. Improving Math Word Problems with Pre-trained Knowledge and Hierarchical Reasoning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3384–3394, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Improving Math Word Problems with Pre-trained Knowledge and Hierarchical Reasoning (Yu et al., EMNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/2021.emnlp-main.272.pdf
Video:
 https://preview.aclanthology.org/auto-file-uploads/2021.emnlp-main.272.mp4
Data
MAWPSMath23K