@inproceedings{chen-etal-2020-question,
    title = "Question Directed Graph Attention Network for Numerical Reasoning over Text",
    author = "Chen, Kunlong  and
      Xu, Weidi  and
      Cheng, Xingyi  and
      Xiaochuan, Zou  and
      Zhang, Yuyu  and
      Song, Le  and
      Wang, Taifeng  and
      Qi, Yuan  and
      Chu, Wei",
    editor = "Webber, Bonnie  and
      Cohn, Trevor  and
      He, Yulan  and
      Liu, Yang",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest_wac_2008/2020.emnlp-main.549/",
    doi = "10.18653/v1/2020.emnlp-main.549",
    pages = "6759--6768",
    abstract = "Numerical reasoning over texts, such as addition, subtraction, sorting and counting, is a challenging machine reading comprehension task, since it requires both natural language understanding and arithmetic computation. To address this challenge, we propose a heterogeneous graph representation for the context of the passage and question needed for such reasoning, and design a question directed graph attention network to drive multi-step numerical reasoning over this context graph. Our model, which combines deep learning and graph reasoning, achieves remarkable results in benchmark datasets such as DROP."
}