Python/Keras program for generating both sentence embeddings and word embeddings jointly. Impelemented for Turkish text only. Modify tokenize function for other languages.
In Progress
Paper:
Pagliardini, Matteo, Prakhar Gupta, and Martin Jaggi. "Unsupervised learning of sentence embeddings using compositional n-gram features." Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). Vol. 1. 2018.
Original Work based on FastText Library