A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings

@article{Artetxe2018ARS,
  title={A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings},
  author={Mikel Artetxe and Gorka Labaka and Eneko Agirre},
  journal={CoRR},
  year={2018},
  volume={abs/1805.06297}
}
Recent work has managed to learn crosslingual word embeddings without parallel data by mapping monolingual embeddings to a shared space through adversarial training. However, their evaluation has focused on favorable conditions, using comparable corpora or closely-related languages, and we show that they often fail in more realistic scenarios. This work proposes an alternative approach based on a fully unsupervised initialization that explicitly exploits the structural similarity of the… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 93 times over the past 90 days. VIEW TWEETS