@inproceedings{yu-etal-2021-improving,
    title = "Improving Math Word Problems with Pre-trained Knowledge and Hierarchical Reasoning",
    author = "Yu, Weijiang  and
      Wen, Yingpeng  and
      Zheng, Fudan  and
      Xiao, Nong",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.emnlp-main.272/",
    doi = "10.18653/v1/2021.emnlp-main.272",
    pages = "3384--3394",
    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 \textbf{R}easoning with \textbf{P}re-trained \textbf{K}nowledge and \textbf{H}ierarchical \textbf{S}tructure (\textbf{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."
}