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.
@article{arxiv.1703.02507,
title = {Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features},
author = {Matteo Pagliardini and Prakhar Gupta and Martin Jaggi},
journal= {arXiv preprint arXiv:1703.02507},
year = {2018}
}