logicnn

logicnn copied to clipboard

An implementation of the following paper in application of sentiment classification

Harnessing Deep Neural Networks with Logic Rules
Zhiting Hu, Xuezhe Ma, Zhengzhong Liu, Eduard Hovy, Eric P. Xing, ACL 2016

• The code is adapted from previous work, written in Python (2.7) and Theano (0.9)

• The SST2 dataset is used

• contact: [email protected]

Data Preparation

• Download and uncompress the pre-trained word2vec to data/w2v/

• run script data/preprocess_data.sh under data/

Running

• run run.sh

• Average performance (accuracy) is around q:0.893, p:0.887 (randomness comes from GPU parallelization)