The code for our paper "AE-smnsMLC: Multi-Label Classification with Semantic Matching and Negative Label Sampling for Product Attribute Value Extraction".
- Python >= 3.6
- torch >= 0.4.1
- numpy >= 1.17.4
- transformers
- sentencepiece
- mojimoji
- The dataset used in the paper is owned by a company which is currently not public available.
To train the model on a dataset, run the train.py file as follows:
python train.py