Adapting NMT to caption translation inWikimedia Commons for low-resource languages

@article{Poncelas2019AdaptingNT,
  title={Adapting NMT to caption translation inWikimedia Commons for low-resource languages},
  author={Alberto Poncelas and Kepa Sarasola and Meghan Dowling and Andy Way and Gorka Labaka and I{\~n}aki Alegria},
  journal={Procesamiento del Lenguaje Natural},
  year={2019},
  volume={63},
  pages={33-40}
}
This paper presents a successful domain adaptation of a general neural machine translation (NMT) system using a bilingual corpus created with captions for images in Wikimedia Commons for the Spanish-Basque and English-Irish pairs. 

Citations

Publications citing this paper.

Transductive Data-Selection Algorithms for Fine-Tuning Neural Machine Translation

Alberto Poncelas, Gideon Maillette de Buy Wenniger, Andy Way
  • ArXiv
  • 2019
VIEW 1 EXCERPT
CITES BACKGROUND
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 24 REFERENCES

2018a. Data selection with feature decay algorithms using an approximated target side

Poncelas, de Buy Wenniger, A. Way2018a Poncelas, G. M. de Buy Wenniger, A. Way
  • 2018

2018b. Feature decay algorithms for neural machine translation

Poncelas, de Buy Wenniger, A. Way2018b Poncelas, G. M. de Buy Wenniger, A. Way
  • In 21st Annual Conference of the European Association
  • 2018