Tilde’s Machine Translation Systems for WMT 2019
By Marcis Pinnis, Rihards Krišlauks, Matīss Rikters. 2019
11 citations recorded by the source corpus.
The paper describes Tilde’s EnglishLatvian and Latvian-English machine translation systems for the WMT 2017 shared task in news translation. Both constrained and unconstrained systems are described. Our constrained systems were ranked as the best performing systems according to the automatic evaluation results. The paper gives details to how we pre-processed training data, the NMT system architecture that we used for training the NMT models, the SMT systems and their usage in NMT-SMT hybrid system configurations.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Ondrej Bojar
- Philipp Koehn
- Rico Sennrich
- Graham Neubig
- Felix Stahlberg
- Barry Haddow
- Matt Post
- Yonatan Belinkov
Citations in the corpus
- Findings of the 2018 Conference on Machine Translation (WMT18) (2018, methodology): “TILDE Tilde (Pinnis et al., 2018)”
- Findings of the 2019 Conference on Machine Translation (WMT19) (2019, methodology): “TILDE-NC-NMT Tilde (Pinnis et al., 2019)”
- Tilde’s Machine Translation Systems for WMT 2017 (2018, methodology): “As NMT systems are sensitive to noise in parallel data (Pinnis et al., 2017a), all parallel data were filtered using the parallel data filtering methods described by Pinnis (2018).”