Domain Attention

Domain Attention Model proposed in paper "Domain Attention Model for Multi-Domain Sentiment Classification" (link), which is accepted by Knowledge Based Systems.

Data

Multi-Domain Sentiment Dataset (version 2.0)

The dataset we used is unprocessed.tar.gz which contains the original data.

Train & Test

For example, you can use the following command to test the model in the MDSD dataset:

python model.py

The parameter settings are list in SharedData which is defined in model.py.

The run-log files of 3 repeated runs (using the default parameters in the scripts) can be found in /run-logs folder, which give the following accuracy results:

The results reported in the paper are averaged through ten runs (10-fold cross validation), which maybe slightly different from the above results.

Notice: you should first download the MDSD dataset and glove word vectors to run this code. The glove version we used is glove.6B.zip.

Code Description

• data_helper.py data loader for the MDSD dataset
• model.py the domain attention model, train and test
• utils.py misc util functions

For any issues, you can contact me via [email protected]