Merge pull request #5 from openai/readme

updated readme

README.md

@@ -1,9 +1,8 @@
-# generating-reviews-discovering-sentiment
-Code for "Learning to Generate Reviews and Discovering Sentiment"
+# Generating Reviews and Discovering Sentiment
 
-This is where we'll be putting code related to the paper [Learning to Generate Reviews and Discovering Sentiment](https://arxiv.org/abs/1704.01444) (Alec Radford, Rafal Jozefowicz, Ilya Sutskever).
+Code for [Learning to Generate Reviews and Discovering Sentiment](https://arxiv.org/abs/1704.01444) (Alec Radford, Rafal Jozefowicz, Ilya Sutskever).
 
-Right now the code supports using the language model as feature extractor.
+Right now the code supports using the language model as a feature extractor.
 
 ```
 from encoder import Model
@@ -12,3 +11,7 @@ model = Model()
 text = ['demo!']
 text_features = model.transform(text)
 ```
+
+This repo also contains the parameters of the multiplicative LSTM model with 4,096 units we trained on the Amazon product review dataset introduced in McAuley et al. (2015) [1]. The dataset in de-duplicated form contains over 82 million product reviews from May 1996 to July 2014 amounting to over 38 billion training bytes. Training took one month across four NVIDIA Pascal GPUs, with our model processing 12,500 characters per second.
+
+[1] McAuley, Julian, Pandey, Rahul, and Leskovec, Jure. Inferring networks of substitutable and complementary products. In *Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining*, pp. 785–794. ACM, 2015.