███████╗███████╗███╗   ███╗███████╗██╗   ██╗ █████╗ ██╗
██╔════╝██╔════╝████╗ ████║██╔════╝██║   ██║██╔══██╗██║
███████╗█████╗  ██╔████╔██║█████╗  ██║   ██║███████║██║
╚════██║██╔══╝  ██║╚██╔╝██║██╔══╝  ╚██╗ ██╔╝██╔══██║██║
███████║███████╗██║ ╚═╝ ██║███████╗ ╚████╔╝ ██║  ██║███████╗
╚══════╝╚══════╝╚═╝     ╚═╝╚══════╝  ╚═══╝  ╚═╝  ╚═╝╚══════╝


DESCRIPTION
  In this task, you are given a textual dialogue i.e. a user utterance along
  with two turns of context, you have to classify the emotion of user utterance
  as one of the emotion classes: Happy, Sad, Angry or Others.

REQUIREMENTS
  ° python 3
  ° pandas
  ° numpy
  ° tensorflow
  ° scikit-learn
  ° keras
  ° nltk
  ° ekphrasis
  ° tweet tokenizer (pip install git+https://github.com/erikavaris/tokenizer.git)
  ° glove data (http://nlp.stanford.edu/data/glove.840B.300d.zip) need to be extracted in the folder data

USAGE
    python train.py -config configuration.config

CONTRIBUTORS
  Sirine Kéfi
  Carine Zhang
  Thibaud Chominot
  Hussem Ben Belgacem
  Guillaume Drapala-Bizouarn


Data provided by Microsoft