Skip to content
/ LaCo Public

The code for our paper "Noisy Multi-Label Text Classification via Instance-Label Pair Correction” (Accepted by NAACL'24)

Notifications You must be signed in to change notification settings

CLIAgroup/LaCo

Repository files navigation

Official code for our paper.

Requirements:

  • python==3.7.10
  • numpy==1.21.2
  • scipy==1.7.2
  • scikit-learn==0.22
  • torch==1.10.0
  • gensim==4.1.2
  • nltk==3.6.5
  • tqdm==4.62.3

Datasets

All datasets are derived from LSAN and LDGN.

Experiments

Data Path

Please confirm the corresponding configuration file. Make sure the data path parameters (data_dir, dataset and etc.) are right in:

main.py

train and eval

bash script/run_ilaco.sh <dataset> <noise_rate> <gpu_id> 

About

The code for our paper "Noisy Multi-Label Text Classification via Instance-Label Pair Correction” (Accepted by NAACL'24)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages