Unsupervised learning of sentence embeddings

The recent tremendous success of unsupervised word embeddings in a multitude of applications raises the obvious question if similar methods could be derived to improve embeddings (i.e. semantic representations) of word sequences as well. We present a simple but efficient unsupervised objective to train distributed representations of sentences. Our method outperforms the state-of-the-art unsupervised models on most benchmark tasks, highlighting the robustness of the produced general-purpose sentence embeddings.

By Matteo Pagliardini, Prakhar Gupta, Martin Jaggi

Codes and Models are available at:

https://github.com/epfml/sent2vec
https://arxiv.org/abs/1703.02507

Download as PDF