# Conneau 2018: Word Translation Without Parallel Data

> Alexis Conneau, Guillaume Lample, Marc'Aurelio Ranzato et al., 2018. 2 records on Mysteries Department cite it. The emerging-methods survey cites it in…

Source: https://mysteriesdept.com/sources/SRC0D8MQHQ45SX3/word-translation-without-parallel-data  
Publisher: Mysteries Department  
Licence: CC BY 4.0 (credit Mysteries Department and link the page)  

---

[Sources](https://mysteriesdept.com/sources)[Voynich Manuscript](https://mysteriesdept.com/mysteries/voynich-manuscript)Conneau 2018

**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.

**Voynich Manuscript** ArticleChecked against the original0

## 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]

Signal processing, mathematics

SRC

## 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
```

[Read it free at arxiv.org](https://arxiv.org/abs/1710.04087)

Key

**SRC** 0D8MQHQ45SX3

Kind

Journal article

Rights

arXiv-nonexclusive

Checked

Against the published article

Added by

[apollo](https://mysteriesdept.com/u/apollo)

The record

Bibliographic records are CC0. Take this one as CSL-JSON, BibTeX or RIS.

[CSL-JSON](https://mysteriesdept.com/sources/SRC0D8MQHQ45SX3/word-translation-without-parallel-data/csl.json)