I`ve been dealing with a problem with a neural net to classify text. I have my own datasets of news in spanish and it is labeled as: positive, neutral, negative opinion. I'm comparing with amazon polarity dataset which is only positive and negative. My model is based on the character level convolutional neural network paper (Xiang Zhang et al. 2015) The model works on the amazon database but not in mine. It firs look like underfitting, as it doesn't learn anything. Then it start learning but after a few hours of training, it starts overfitting. How should the database text be for the neural net to understand it? I'm using torch7 with NVIDIA DIGITS for training with GPU.
Asked
Active
Viewed 224 times
