EMNLP 2021finding12 citations

A Pretraining Numerical Reasoning Model for Ordinal Constrained Question Answering on Knowledge Base

Yu Feng, Jing Zhang, Gaole He, Wayne Xin Zhao, Lemao Liu, Quan Liu, Cuiping Li, Hong Chen

Abstract

Knowledge Base Question Answering (KBQA) is to answer natural language questions posed over knowledge bases (KBs). This paper targets at empowering the IR-based KBQA models with the ability of numerical reasoning for answering ordinal constrained questions. A major challenge is the lack of explicit annotations about numerical properties. To address this challenge, we propose a pretraining numerical reasoning model consisting of NumGNN and NumTransformer, guided by explicit self-supervision signals. The two modules are pretrained to encode the magnitude and ordinal properties of numbers respectively and can serve as model-agnostic plugins for any IR-based KBQA model to enhance its numerical reasoning ability. Extensive experiments on two KBQA benchmarks verify the effectiveness of our method to enhance the numerical reasoning ability for IR-based KBQA models.

BibTeX
@inproceedings{feng-etal-2021-pretraining-numerical,
    title = "A Pretraining Numerical Reasoning Model for Ordinal Constrained Question Answering on Knowledge Base",
    author = "Feng, Yu  and
      Zhang, Jing  and
      He, Gaole  and
      Zhao, Wayne Xin  and
      Liu, Lemao  and
      Liu, Quan  and
      Li, Cuiping  and
      Chen, Hong",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
    month = nov,
    year = "2021",
    address = "Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.findings-emnlp.159/",
    doi = "10.18653/v1/2021.findings-emnlp.159",
    pages = "1852--1861"
}
A Pretraining Numerical Reasoning Model for Ordinal Constrained Question Answering on Knowledge Base · EMNLP 2021