charrtay / navigating-nlp

Resources for upskilling on NLP.

navigating-nlp

Resources for upskilling on NLP.

Tutorials

1. Featurize free-form text data using mmlspark on top of primitives in SparkML via a single transformer in this official mmlspark notebook
2. Good NLTK tutorial, albeit with some fun Python code fixes needed :) - NLTK Tutorial: Natural Language Processing w/ Python (for a working notebook see notebooks folder)

Examples

1. scikit-learn's document clustering with k-means official example

Books

1. Official NLTK book online
2. Python 3 Text Processing with NLTK 3 Cookbook

Docs for Training at Scale

1. Document classification with pyspark with HDInsight on Azure
2. NLP with MLLib from official Spark Docs
3. NLTK and pyspark from Anaconda Docs

Blog Articles

1. Python/scikit-learn: Calculating TF/IDF on How I met your mother transcripts for TF/IDF with scikit-learn

Docs for Operationalization of Models - Get That NLP Model Up as a Real Service on Azure

Azure Machine Learning Operationalization