Aligned word vectors

We are publishing aligned word vectors for 44 languages based on the pre-trained vectors computed on Wikipedia using fastText. The alignments are performed with the RCSLS method described in Joulin et al (2018).

Vectors

The aligned vectors can be downloaded from:

Afrikaans: text	Arabic: text	Bulgarian: text	Bengali: text
Bosnian: text	Catalan: text	Czech: text	Danish: text
German: text	Greek: text	English: text	Spanish: text
Estonian: text	Persian: text	Finnish: text	French: text
Hebrew: text	Hindi: text	Croatian: text	Hungarian: text
Indonesian: text	Italian: text	Korean: text	Lithuanian: text
Latvian: text	Macedonian: text	Malay: text	Dutch: text
Norwegian: text	Polish: text	Portuguese: text	Romanian: text
Russian: text	Slovak: text	Slovenian: text	Albanian: text
Swedish: text	Tamil: text	Thai: text	Tagalog: text
Turkish: text	Ukrainian: text	Vietnamese: text	Chinese: text

Format

The word vectors come in the default text format of fastText. The first line gives the number of vectors and their dimension. The other lines contain a word followed by its vector. Each value is space separated.

License

The word vectors are distributed under the Creative Commons Attribution-Share-Alike License 3.0.

References

If you use these word vectors, please cite the following papers:

[1] A. Joulin, P. Bojanowski, T. Mikolov, H. Jegou, E. Grave, Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion

@InProceedings{joulin2018loss,
  title={Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterion},
  author={Joulin, Armand and Bojanowski, Piotr and Mikolov, Tomas and J\'egou, Herv\'e and Grave, Edouard},
  year={2018},
  booktitle={Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing},
}

[2] P. Bojanowski*, E. Grave*, A. Joulin, T. Mikolov, Enriching Word Vectors with Subword Information

@article{bojanowski2017enriching,
  title={Enriching Word Vectors with Subword Information},
  author={Bojanowski, Piotr and Grave, Edouard and Joulin, Armand and Mikolov, Tomas},
  journal={Transactions of the Association for Computational Linguistics},
  volume={5},
  year={2017},
  issn={2307-387X},
  pages={135--146}
}