Word Translation Without Parallel Data

@article{Conneau2017WordTW,
  title={Word Translation Without Parallel Data},
  author={Alexis Conneau and Guillaume Lample and Marc'Aurelio Ranzato and Ludovic Denoyer and Herv{\'e} J{\'e}gou},
  journal={CoRR},
  year={2017},
  volume={abs/1710.04087}
}
State-of-the-art methods for learning cross-lingual word embeddings have relied on bilingual dictionaries or parallel corpora. Recent studies showed that the need for parallel data supervision can be alleviated with character-level information. While these methods showed encouraging results, they are not on par with their supervised counterparts and are limited to pairs of languages sharing a common alphabet. In this work, we show that we can build a bilingual dictionary between two languages… CONTINUE READING
Highly Influential
This paper has highly influenced a number of papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 69 citations. REVIEW CITATIONS

8 Figures & Tables

Topics

Statistics

05010020172018
Citations per Year

70 Citations

Semantic Scholar estimates that this publication has 70 citations based on the available data.

See our FAQ for additional information.