This article is for those who are getting started with fastText. fastText is a text representation and classification library from Facebook Research developed by FAIR lab. Classification of text documents is an important natural language processing (NLP) task. It is originally written in C++ but can be accessed using Python interface. It is massively fast. See references for two defining papers.
In this article we’ll discuss Python installation of fastText. pip and cython are pre-requisites, install them if not already installed:
#Installing pip sudo apt-get install pip
Now, install cython
#Installing Cython pip install cython
Finally install fastText which may also download other missing packages like numpy for us.
#Installing fastText pip install fasttext
And we are done!
See next post Text Classification With Python Using fastText.
- fastTex – Facebook Research
- Representation: Enriching Word Vectors with Subword Information, Piotr Bojanowski, Edouard Grave, Armand Joulin and Tomas Mikolov, 2016
- Classification: Bag of Tricks for Efficient Text Classification, Armand Joulin, Edouard Grave, Piotr Bojanowski, Tomas Mikolov, 2016