Skip to content

Latest commit

 

History

History
47 lines (39 loc) · 1.44 KB

README.md

File metadata and controls

47 lines (39 loc) · 1.44 KB
Raw

UniST

Code for our paper Unified Semantic Typing with Meaningful Label Inference at NAACL 2022.

Requirements

  • pytorch == 1.9.1
  • transformers == 4.10.2
  • scikit-learn

Data

UFET

Download UFET dataset and place the crowdsourced portion under data/ufet.

TACRED

Download TACRED dataset to data/tacred.

MAVEN

Download MAVEN dataset to data/maven.

FewRel

Download FewRel dataset to data/fewrel and run

python data/fewrel/process_fewrel.py

Experiments

The training scripts are provided under ./scripts. For example, to train a UniST base model on TACRED, run

bash ./scripts/run_tacred.sh

Citing

@inproceedings{huang-etal-2022-unified,
    title = "Unified Semantic Typing with Meaningful Label Inference",
    author = "Huang, James Y.  and
      Li, Bangzheng  and
      Xu, Jiashu  and
      Chen, Muhao",
    booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.naacl-main.190",
    pages = "2642--2654"
}