Common Sense Net at SemEval2020-Task4

by Soumya Ranjan Dash*, Sandeep Routray*, Prateek Varshney*, Ashutosh Modi

Siamese BERT for ComVE

This repository gives a Pytorch implementation of the method in the system description paper.

Prerequisites

• Python3.5 (or higher)
• Pytorch 1.5.1
• numpy
• transformers
• csv

Installation

git clone https://github.com/soumyardash/SemEval2020-Task4.git
cd SemEval2020-Task4/
pip install transformers

Citation

If our method is useful for your research, please consider citing:

  @misc{dash2020csnet,
    title={CS-NET at SemEval-2020 Task 4: Siamese BERT for ComVE},
    author={Soumya Ranjan Dash and Sandeep Routray and Prateek Varshney and Ashutosh Modi},
    year={2020},
    eprint={2007.10830},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
  }

  @inproceedings{wangsemeval,
      title = "{S}em{E}val-2020 Task 4: Commonsense Validation and Explanation",
      author = "Wang, Cunxiang  and
        Liang, Shuailong  and
        Jin, Yili  and
        Wang, Yilong  and
        Zhu, Xiaodan  and
        Zhang, Yue",
      booktitle = "Proceedings of The 14th International Workshop on Semantic Evaluation",
      year = "2020",
      publisher = "Association for Computational Linguistics",
  }