lanzhuzhu / Meta-reweighting4DSRC

The implementation of "Meta-Learning for Neural Relation Classification with Distant Supervision"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Meta-reweighting4DSRC

The implementation of "Meta-Learning for Neural Relation Classification with Distant Supervision"

Getting Started

Required

  • python >= 3.5
  • pytorch >= 1.3.0

Data

Considering the copyright of Wiki-KBP and TACRED, we release the intermediate file of our dataset. You can download from here and put the kbp_extend_data file in the project.

Running

The last parameter represents the index of five reference datasets.

python meta_reweighting.py 0

Citation

Please consider citing the following paper if you find our codes helpful. Thank you!

@inproceedings{li2020meta,
  title={Meta-Learning for Neural Relation Classification with Distant Supervision},
  author={Li, Zhenzhen and Nie, Jian-Yun and Wang, Benyou and Du, Pan and Zhang, Yuhan and Zou, Lixin and Li, Dongsheng},
  booktitle={Proceedings of the 29th ACM International Conference on Information \& Knowledge Management},
  pages={815--824},
  year={2020}
}

About

The implementation of "Meta-Learning for Neural Relation Classification with Distant Supervision"


Languages

Language:Python 100.0%