A library for text representation and classification by Facebook.
FastTextfastText is an open source library designed to help build scalable solutions for text representation and classification. It is developedDeveloped by the Facebook AI Research (FAIR)., Itit transforms text into continuous vectors that can be used on any language related task. It uses concepts of natural language processing and machine learning for efficient text classification and learning word vector representations.
fastText only works on CPU for accessibility. It is implemented in the Caffe2 library which can be run on GPU.
FAIR proposed fastText in 2016. It is an extension to Word2Vec, a model for learning vector representation. It breaks down words into various sub-words then feeds them to the neural network while Word2Vec processes individual words.
Facebook AI Research
Get started · fastText
Word2Vec and FastText Word Embedding with Gensim – Towards Data Science