Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features

Code

• github.com/epfml/sent2vec
  OfficialIn papernone★ 0
• github.com/celento/sent2vec
  none★ 0
• github.com/chalothon/Sentence2Vec
  none★ 0
• github.com/dantetam/twitterServerAuth
  none★ 0
• github.com/SimengSun/CIS530-project
  pytorch★ 0

Abstract

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.

Tasks

Reproductions