LIUM Machine Translation Systems for WMT17 News Translation Task

@inproceedings{GarcaMartnez2017LIUMMT,
  title={LIUM Machine Translation Systems for WMT17 News Translation Task},
  author={Mercedes Garc{\'i}a-Mart{\'i}nez and Ozan Caglayan and Walid Aransa and Adrien Bardet and Fethi Bougares and Lo{\"i}c Barrault},
  booktitle={WMT},
  year={2017}
}
This paper describes LIUM submissions to WMT17 News Translation Task for English↔German, English↔Turkish, English→Czech and English→Latvian language pairs. We train BPE-based attentive Neural Machine Translation systems with and without factored outputs using the open source nmtpy framework. Competitive scores were obtained by ensembling various systems and exploiting the availability of target monolingual corpora for back-translation. The impact of back-translation quantity and quality is also… CONTINUE READING
Related Discussions
This paper has been referenced on Twitter 12 times. VIEW TWEETS

From This Paper

Figures, tables, results, and topics from this paper.

Key Quantitative Results

  • The impact of back-translation quantity and quality is also analyzed for English→Turkish where our post-deadline submission surpassed the best entry by +1.6 BLEU.

Explore Further: Topics Discussed in This Paper

References

Publications referenced by this paper.
Showing 1-10 of 27 references

Nematus: a Toolkit for Neural Machine Translation

EACL • 2017
View 6 Excerpts
Highly Influenced

Conditional gated recurrent unit with attention mechanism

Orhan Firat, Kyunghyun Cho.
http://github.com/nyu-dl/dl4mttutorial/blob/master/docs/cgru.pdf. • 2016
View 4 Excerpts
Highly Influenced

Re - current neural network based language model Morphological analysis with limited resources : Latvian example

Tomas Mikolov, Martin Karafiát, Jan Cernocký Lukás Burget, Sanjeev Khudanpur
2010
View 4 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…