GATT-For-Aspect

Code for AACL-IJCNLP 2020 paper: Graph Attention Network with Memory Fusion for Aspect-level Sentiment Analysis

Dependency

• python 3.6+

• PyTorch 1.1.0+

• scipay 1.5.2+

• others

  • nltk
  • numpy
  • sklearn

data

For get data,you can in this link

Dependency tree-graph

For get Dependency tree-graph , you can run commands like this: python denpendent-graph.py

Train and Test

you can run commands like this: python train.py --dataset rest14

Train and Test

Contact Me

[email protected]

Cite our paper if you find our work is helpful~

@inproceedings{yuan-etal-2020-graph, title = "Graph Attention Network with Memory Fusion for Aspect-level Sentiment Analysis", author = "Yuan, Li and Wang, Jin and Yu, Liang-Chih and Zhang, Xuejie", booktitle = "Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing", month = dec, year = "2020", pages = "27--36", }