COLING 2020main36 citations

An Enhanced Knowledge Injection Model for Commonsense Generation

Zhihao Fan, Yeyun Gong, Zhongyu Wei, Siyuan Wang, Yameng Huang, Jian Jiao, Xuanjing Huang, Nan Duan

Abstract

Commonsense generation aims at generating plausible everyday scenario description based on a set of provided concepts. Digging the relationship of concepts from scratch is non-trivial, therefore, we retrieve prototypes from external knowledge to assist the understanding of the scenario for better description generation. We integrate two additional modules into the pretrained encoder-decoder model for prototype modeling to enhance the knowledge injection procedure. We conduct experiment on CommonGen benchmark, experimental results show that our method significantly improves the performance on all the metrics.

BibTeX
@inproceedings{fan-etal-2020-enhanced,
    title = "An Enhanced Knowledge Injection Model for Commonsense Generation",
    author = "Fan, Zhihao  and
      Gong, Yeyun  and
      Wei, Zhongyu  and
      Wang, Siyuan  and
      Huang, Yameng  and
      Jiao, Jian  and
      Huang, Xuanjing  and
      Duan, Nan  and
      Zhang, Ruofei",
    editor = "Scott, Donia  and
      Bel, Nuria  and
      Zong, Chengqing",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://aclanthology.org/2020.coling-main.182/",
    doi = "10.18653/v1/2020.coling-main.182",
    pages = "2014--2025"
}
An Enhanced Knowledge Injection Model for Commonsense Generation · COLING 2020