navigating-nlp

My resources for learning NLP with Python.

This project is maintained by michhar

Resources

Tutorials

  1. Gensim official Docs Tutorial
  2. Natural Language Processing with NLTK and Gensim Video
  3. A Word2Vec Keras tutorial Tutorial
  4. Language Understanding with Recurrent Networks and CNTK Tutorial
  5. Vector Representations of Words with TensorFlow Tutorial
  6. Word2Vec word embedding tutorial in Python and TensorFlow Tutorial

Courses and Course Materials

  1. Stanford Deep Learning for NLP (cs224n) Course Material

Examples

  1. Document clustering with k-means official scikit-learn Example
  2. Featurize free-form text data using mmlspark on top of primitives in SparkML via a single transformer in this official mmlspark Notebook
  3. Sequence Classification with CNTK Example
  4. Sequence2Sequence with CNTK Example

NLP-Specific Packages

  1. allennlp: Deep Learning for NLP from AllenNLP built on PyTorch Ref - good for conditional random field, encoders/decoders, reading comprehension, semantic role, etc.
  2. gensim: topic modelling Docs - good for word2vec, semantic similarity, LDA, LSA, etc.
  3. nltk: Natural Language Toolkit Docs - good for tokenization, stemming, tagging, parsing, corpora, etc. …

NLP at Scale

  1. Document classification with pyspark with HDInsight on Azure Doc

Blog Articles

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

Kaggle

  1. Toxic Comment Classification Challenge Competition

Books