- NLTK
- TextBlob
- Spacy
- Gensim
- CoreNLP
Textblob is older than spacy. It is built on top of NLTK and provides options. Like to do classification i can choose between naive bayes classifier or decision tree classifier. All the classification algorithm is straight away picked from nltk package. Textblob is for prototyping & pocs more.
SpaCy on the other hand is written in cython and is fast & state of the art. Spacy is called more production ready. It gives options to extend framework with Keras.
Gensim , it's robust, efficient, and scalable. you don't use gensim for general NLP. Gensim is a well-optimized library for topic modeling and document similarity analysis. its Latent Dirichlet Allocation (LDA) implementation, are best-in-class.
CoreNLP by Stanford
SyntaxNet
https://github.com/tensorflow/models/tree/master/research/syntaxnet
Neural Net based NLP with support of Tensorflow.
SyntaxNet is a library for researching NLP models, while spaCy is a library for applying NLP models in production.
References :-