pwr2000/deep-learning-nlp-pydata

deep-learning-nlp

Resources and notebook for "Deep Learning and Modern NLP" Workshop for PyData Miami 2019

Environment Setup

This tutorial requires an existing installation of Anaconda 3 (tested with Python 3.6). From the root directory of the repo, run:

conda env create -f environment.yml
source activate deep-learning-nlp

Datasets used in Tutorials

Data for these tutorials are sourced from various locations, and prepared in advance into pickled Pandas DataFrames. The original sources of the data can be found in the links below.

• Perceptron
  • Stanford Large Movie Review Dataset
  • Stack Overflow Q&A
• LSTM Classification
  • R8 of Reuters 21578
• Part of Speech Tagging
  • Sample of the Penn Treebank dataset from the NLTK Corpora
• Machine Translation
  • European Parliament Proceedings Parallel Corpus 1996-2011