0
Word Translation Without Parallel Data
Alexis Conneau, Guillaume Lample, Marc'Aurelio Ranzato et al., 2018. ICLR 2018.
Shows that a bilingual dictionary can be learned without parallel text by aligning monolingual word embeddings through adversarial training followed by refinement.
What it's used for here
The emerging-methods survey cites it in its section on unsupervised cross-lingual embedding alignment and its limits.
Cited by on this site 2 records
2 methods surveys
SRCSignal processing, mathematics
Cite it
Conneau, A., Lample, G., Ranzato, M., Denoyer, L., & Jégou, H. (2018). Word Translation Without Parallel Data. ICLR 2018. https://arxiv.org/abs/1710.04087
@article{conneau2018word,
author = {Conneau, Alexis and Lample, Guillaume and Ranzato, Marc'Aurelio and Denoyer, Ludovic and Jégou, Hervé},
title = {Word Translation Without Parallel Data},
journal = {ICLR 2018},
year = {2018},
url = {https://arxiv.org/abs/1710.04087}
}TY - JOUR TI - Word Translation Without Parallel Data AU - Conneau, Alexis AU - Lample, Guillaume AU - Ranzato, Marc'Aurelio AU - Denoyer, Ludovic AU - Jégou, Hervé PY - 2018 JO - ICLR 2018 UR - https://arxiv.org/abs/1710.04087 ER -
Conneau, Alexis et al.. “Word Translation Without Parallel Data.” ICLR 2018 (2018).