FastText

fastText is an open source library designed to help build scalable solutions for text representation and classification. Developed by the Facebook AI Research (FAIR), it 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.