skreddy99 / Digitalist_NLP_Workshop

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Digitalist_NLP_Workshop

Welcome to Digitalist NLP Workshop in Mar 2018. I have added some files in this repo. Please do the following.

  • Step1: Create a seperate directory.
  • Step2: Please download all the files in this repo into that directory.

If you could not, do not worry. I will discuss them in the workshop.

Also complete the following few tasks.

  • Task(1): Install any python editor of your choice. I prefer PyCharm Community Edition 2016.3 (though a later version is available, I had difficulties in running it on my iMac). You can find the relevant links here. https://www.jetbrains.com/pycharm/download/previous.html. I will use the editor to view and code and discuss.

  • Task(2): Install Anaconda Navigator. This will help you install certain basic packages like Numpy, Pandas, Keras, etc. (https://docs.continuum.io/anaconda/install/). I may talk about these packages but nevertheless you need these packages for future ML experiments Task(3): Please download nltk and all the text corpora available at http://www.nltk.org/. (Optional: In addition, you MAY also get Core NLP from Stanford at https://stanfordnlp.github.io/CoreNLP/.)

I am excited to about the workshop. As you can image, NLP is tranforming the world. I will explain NLP concepts and discuss tips on how to use NLP and build solutions.

Here are some statements to keep in mind:

  • (a) I assume that you are familiar with programming, preferably python.
  • (b) The course is not about teaching programing. It is about teaching how NLP works, explain various concepts in NLP and show a few exampes of existing code snippets in python that implement NLP concepts.
  • (c) Developing NLP solutions using frameworks (like Tensorflow, Caffe2, PyTorch, MLlib, etc.) is increasingly becoming easier. What remains difficult is the basic understanding of NLP concepts. Here is where I will try to spend more time.
  • (d) Be prepared to ask a lot of questions.

About


Languages

Language:Python 100.0%