From 7ceaa53a260e55dfa0e76c83dcb955920ea93f1f Mon Sep 17 00:00:00 2001
From: tfavory <43109272+tfavory@users.noreply.github.com>
Date: Sun, 9 Sep 2018 20:11:33 +0800
Subject: [PATCH] Update README.md

Link to books in the corpus of poems
Minor changes
---
 README.md | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/README.md b/README.md
index 8c17691..6c2a67d 100644
--- a/README.md
+++ b/README.md
@@ -1,19 +1,23 @@
 # pmlg-poem-generator
 
 This is a poem generator trained with Gated Recurrent Units (GRU) on a corpus of poems including those in:
-* Poems every child should know
-* Some other poems
-* And some more poems
+* [Poems Every Child Should Know](http://www.gutenberg.org/ebooks/16436), by Mary E. Burt
+* [Poems](http://www.gutenberg.org/ebooks/52546), by Thomas Hall Shastid
+* [Poems of Progress and New Thought Pastels](http://www.gutenberg.org/ebooks/3228), by Ella Wheeler Wilcox
+* [Poems Teachers Ask For](http://www.gutenberg.org/ebooks/18909)
+* [Poems Teachers Ask For, Book Two](http://www.gutenberg.org/ebooks/19469)
+* [The Pied Piper of Hamelin, and Other Poems](http://www.gutenberg.org/ebooks/42850), by Robert Browning
 
 Most of the code comes from [Tensorflow's text generation tutorial](https://github.com/tensorflow/tensorflow/blob/r1.10/tensorflow/contrib/eager/python/examples/generative_examples/text_generation.ipynb).
 
 Please refer to the notebook for an overview of the results.
 
-## To do next
+## Improvement ideas
 
 ### Short term:
 * Clean the corpus
 * Find more data
+* Save a model
 * Try LSTM
 * Train a model based on sequences of words instead of characters
 
@@ -23,7 +27,5 @@ Please refer to the notebook for an overview of the results.
 
 The idea is to generate the rhymes first, and then write the lines from the last word to the first. This process makes sure that the generated poems rhyme.
 
-* Learn to count syllables?
-
 ### Long term goals
 * Generate other kind of text (Haiku, magazines, articles, books...)