The TALP-UPC Machine Translation Systems for WMT19 News Translation Task: Pivoting Techniques for Low Resource MT
By Noe Casas, José A. R. Fonollosa, Carlos Escolano, Christine Basta, Marta Ruiz Costa-jussà. 2019
16 citations recorded by the source corpus.
In this article, we describe the TALP-UPC research group participation in the WMT19 news translation shared task for Kazakh-English. Given the low amount of parallel training data, we resort to using Russian as pivot language, training subword-based statistical translation systems for Russian-Kazakh and Russian-English that were then used to create two synthetic pseudo-parallel corpora for Kazakh-English and English-Kazakh respectively. Finally, a self-attention model based on the decoder part of the Transformer architecture was trained on the two pseudo-parallel corpora.
Subfields: Artificial Intelligence, Language and Linguistics
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
In Language and Linguistics
- Marta Ruiz Costa-jussà
- Ondrej Bojar
- Mathias Müller
- Philipp Koehn
- Yvette Graham
- Barry Haddow
- Matt Post
Citations in the corpus
- Findings of the 2019 Conference on Machine Translation (WMT19) (2019, methodology): “TALP_UPC_2019 TALP Research Center, Universitat Politècnica de Catalunya (Casas et al., 2019)”
- Using natural language prompts for machine translation (2022, unknown): “In particular, we report the results of Casas et al. (2019) for English-Kazakh, the results of Xia et al. (2019) for German-French and Marie et al. (2019) for German-Czech.”