The QT21 Combined Machine Translation System for English to Latvian
| Autor: | Ondrej Bojar, Frédéric Blain, Marcis Pinnis, Philip Williams, Wilker Aziz, Jasmijn Bastings, Alex Waibel, François Yvon, Ngoc-Quan Pham, Jan-Thorsten Peter, Franck Burlot, Lucia Specia, Miguel Rios, Hermann Ney, Jan Niehues, Valters Sics |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Computer science
business.industry Latvian 02 engineering and technology computer.software_genre language.human_language 03 medical and health sciences 0302 clinical medicine 030221 ophthalmology & optometry 0202 electrical engineering electronic engineering information engineering language 020201 artificial intelligence & image processing Artificial intelligence Machine translation system business computer Natural language processing |
| Zdroj: | WMT Scopus-Elsevier Peter, J-T, Ney, H, Bojar, O, Pham, N-Q, Niehues, J, Waibel, A, Burlot, F, Yvon, F, Pinnis, M, Sics, V, Bastings, J, Rios, M, Williams, P, Blain, F & Specia, L 2017, The QT21 Combined Machine Translation System for English to Latvian . in Proceedings of the Second Conference on Machine Translation, Volume 2: Shared Task Papers . pp. 348-357, Second Conference on Machine Translation, Copenhagen, Denmark, 7/09/17 . https://doi.org/10.18653/v1/W17-4734 |
| DOI: | 10.18653/v1/w17-4734 |
| Popis: | This paper describes the joint submis- sion of the QT21 projects for the English → Latvian translation task of the EMNLP 2017 Second Conference on Ma- chine Translation (WMT 2017). The sub- mission is a system combination which combines seven different statistical ma- chine translation systems provided by the different groups. The systems are combined using either RWTH’s system combination approach, or USFD’s consensus-based system- selection approach. The final submission shows an improvement of 0.5 B LEU compared to the best single system on newstest2017. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|