This is a course project for the course Natural Language Understanding at ETH.

This code is written in python. To use it you will need:

• Python 3.6
• A recent version of NumPy
• scikit-learn
• NLTK 3
• Tensorflow
• pandas

To reproduce the result, run ./reproduce.sh. The script requires virtualenv to be installed.

• A Simple and Effective Approach to the Story Cloze Test link
• Story Comprehension for Predicting What Happens Next link
• Two Discourse Driven Language Models for Semantics link
• Skip-Thought Vectors link