IMDB Sentiment Analysis

This is the final project of Machine Learning Courses in Huazhong University of Science and Technology, School of Artificial Intelligence and Automation

Training

To train a model (CNN, LSTM, Transformer), simply run

python train.py --cfg <./model/xxx> --save <./save/>

You can change the configuration in config.

Model

LSTM

we follow the origin LSTM as possible

CNN

we adopt the methods mentioned in Effective Use of Word Order for Text Categorization with Convolutional Neural Networks

Transformer

We use the original Transformer Encoder as Attention is all you need and use the concept of CLS Token as BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Experiment result

Model Comparison

LSTM

Batch size

Embedding Size

Drop out

Weight decay

Number layers

Number of LSTM blocks

CNN

out channel size

multi scale filter