Learning to Generate Reviews and Discovering Sentiment

ICLR 2018 Alec RadfordRafal JozefowiczIlya Sutskever

We explore the properties of byte-level recurrent language models. When given sufficient amounts of capacity, training data, and compute time, the representations learned by these models include disentangled features corresponding to high-level concepts... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Compare
Sentiment Analysis SST-2 Binary classification bmLSTM Accuracy 91.8 # 9
Subjectivity Analysis SUBJ Byte mLSTM Accuracy 94.60 # 3