Pagliardini, MatteoGupta, PrakharJaggi, Martin2017-06-212017-06-212017-06-212017https://infoscience.epfl.ch/handle/20.500.14299/1385301703.02507v3The 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.text::report::research report