PRQA-MultitaskAttentiveNet
Data and codes for "Answer Identification from Product Reviews for User Questions by Multi-task Attentive Network"(AAAI-2019). Requirments: python 3.5+, tensorflow 1.6+, keras 2.0+, NLTK
Preparation
Download pre-trained embedding dictionary "glove.twitter.27B.50d.txt" on https://nlp.stanford.edu/projects/glove/
Running
python MAIN.py
Note
Set "data path" and "model parameters" at the top lines of MAIN.py.