Dataset and code for our AAAI 2020 paper "Replicate, Walk, and Stop on Syntax: an Effective Neural Network Model for Aspect-Level Sentiment Classification"

• Python 3.6
• PyTorch 1.2.0
• NumPy 1.17.2
• GloVe pre-trained word vectors:
  • Download pre-trained word vectors here.
  • Extract the glove.840B.300d.zip to the /glove/ folder.

An easy way to install this code with anaconda environment:

conda create -n repwalk python=3.6
conda activate repwalk
pip install -r requirements.txt

Training the model:

python train.py --dataset [dataset]

Show help message and exit:

python train.py -h

If this work is helpful, please cite as:

@inproceedings{zheng2020replicate,
  title={Replicate, Walk, and Stop on Syntax: an Effective Neural Network Model for Aspect-Level Sentiment Classification},
  author={Yaowei, Zheng and Richong, Zhang and Samuel, Mensah and Yongyi, Mao},
  booktitle={AAAI},
  year={2020}
}

MIT