Neural Machine Translation
Open workshop with Kyunghyun Cho
Donostia, 2017-05-29
Trends in Neural Machine Translation (Olof Mogren, 2016)
The third generation of machine translation systems is currently under active development. After initially dominating the field, rule-based machine translation (RBMT) systems have been gradually replaced by data-driven approaches in the last two decades, with statistical machine translation (SMT) systems prevailing as the main paradigm. In the last two years, deep learning approaches have significantly impacted the field, with the rise of neural machine translation (NMT) as the new state-of-the-art in automated translation. This event presents advanced results in the field, in particular for machine translation of Basque.
Context:
The MODELA project was created to advance research and development in deep-learning approaches to machine translation and to address the many challenges of Basque machine translation. The project is financed by the Basque Government and is being carried out by the following entities: Ametzagaiña, Elhuyar, ISEA, UPV/EHU (IXA group) and Vicomtech-IK4.
Guest:
The main speaker will be Kyunghyun Cho (Center for Data Science, New York University), who is an eminent researcher in the area, the most referenced on NMT, a field in which he has obtained a Google prize. Additionally, he is a a brilliant speaker.
Date: May 29, 2017, 11:00
Place: UPV/EHUko Informatika Fakultatea, Manuel de Lardizabal 1, 20018 Donostia (map)
Schedule:
- 11.00-11.15: Introduction and presentation of the project
- 11.15-12.30: Neural Machine Translation (Kyunghyun Cho)
- 12.30-13.15: First results in the Modela project
Sponsor: Modela project and University of the Basque Country
Next day, on Tuesday May 30, at 15:00 he will be with the students of our Master on Language Technology
After finishing our Erasmus Mundus LCT Master in 2016 
The PhD student will be involved in all stages of the corpus building process, thus having the opportunity to gather translation data relevant to his/her specific research interest. The student will work autonomously on the development of the metadata labelset and on collecting translation data, on the basis of which he or she will conduct quantitative and/or qualitative analyses for his/her thesis. Work will be carried out in close collaboration with the project’s two principal investigators and two MA students. 
Aims:Members of the group have chosen the name 
Aims:The team has continued developing the 
Aims: Each member of the group is focusing on the pair of languages in which he/she is fluent. Based on the program called Apertium, for example, they have started working on a translator for the language combination French-Occitan, so that they can later develop a linguistic analyzer for Occitan. They have also been working on a Tetum-Portuguese translator (the two official languages spoken on the island of Timor) with the same program. Others have started preparing lexical transfers (they will try to do the same with dependency transfers) for the English-Spanish combination using Matxin. This exact same program also allows the creation of a English-Welsh translator, as well as a translator for English-Basque (one such translator already exists, but some errors must be identified and corrected). The latter will be applied in the field of medicine.