This is a pytorch implementation for Interactive Attention Networks for Aspect-Level Sentiment Classification (Dehong Ma et al, IJCAI 2017).
pytorch 1.0.0
numpy
spacy
-
Download the 300-dimensional pre-trained word vectors from Glove and save it in the 'data' folder as 'data/glove.840B.300d.txt'
-
Use the following command to run the code.
python main.py
Dataset | Accuracy |
---|---|
Laptop | 70.376 |
Restaurant | 77.679 |
During the procedure of implementation, the code in lpq29743/IAN is referenced.