Update readme

2017-07_Seminar/docker/Readme.md

@@ -7,7 +7,7 @@ This folder contains a dockerfile that installs a Python 3.6, Keras 2.0.5 and Te
 
 Build the docker container:
 ```
-docker build . -t dl4nlp
+docker build ./docker/dockerfile -t dl4nlp
 ```
 
 

README.md

@@ -3,6 +3,16 @@ Hands-on tutorial on deep learning with a special focus on Natural Language Proc
 
 This GIT repository accompanies the UKP lectures and seminars on Deep Learning for Natural Language Processing. In contrast to other tutorials, this tutorial focuses on the usage of deep learning methods. 
 
+# Deep Learning for NLP - Seminar - July 2017
+In July 2017 I updated the slides to the most recent Python and Keras version. The slides as well as the source code is available in the folder **[2017-07_Seminar](2017-07_Seminar/)**. The code in the folder can be run with either Python 2.7 or Python 3.6, with Keras 2.0.5 and with Theano (0.9.0) or TensorFlow (1.2.1) as backend.
+
+Four different deep learning models for NLP are covered in the folder:
+1. Feed Forward Architecture for Sequence Classification (e.g. POS, NER, Chunking)
+2. Convolutional Neural Network for Sentence / Text Classification (e.g. sentiment classification)
+3. Convolutional Neural Network for Relation Extraction (e.g. semantic relation extration)
+4. Long-Short-Term-Memory (LSTM)-Networks for Sequence Classificaiton 
+
+
 # Deep Learning for NLP - Seminar - Nov. 2016
 In November 2016 I gave a seminar at the University of Duisburg-Essen. The slides as well as the source code is available in the folder **[2016-11_Seminar](2016-11_Seminar/)**. In the seminar I use Python 2.7, Theano 0.8.2, and Keras 1.1.1 to model four different deep learning models for NLP: