MT@BZ

Machine Translation at South Tyrolean Institutions (pilot study)

  • Project duration: May 2021 - May 2022
  • Project status:
    Ongoing

In this project, we aim to conduct a preliminary study on machine translation (MT) at South Tyrolean institutions, e.g. Free University of Bolzano, Province of Bolzano, etc. Neither of them employs a customized machine translation software already, but they have high translation demands, to some extent repetitive and structured texts and specific needs related to the local variety of German. Customized MT could therefore represent an improvement into their translation process. To do so we need a huge amount of parallel segments, ideally several hundreds of thousands up to a million.

In particular, in this project we look into the possibilities of building aligned parallel corpora with their institutional documents. In order to build the corpora, we seek already aligned texts (i.e. translation memories), or collect and align them afterwards. The second option would require also an automated process (e.g. web crawler) and therefore the collaboration of IT-personnel. In both cases, we contact the institutions and pursue a collaboration. In addition, we evaluate the most suitable software for our customization among those present in the scientific-commercial landscape, also getting in contact with foreign institutions that have already conducted similar experimentations in order to initiate scientific interchange.

The results will consist in one or more parallel corpora to feed into a selected MT software, with which we would be able to start a customization. Goal of this project is also to define a greater research project on machine translation for South Tyrolean institutions, which we aim to submit to international funding programs (e.g. Interreg).

Publications
Anpassungsbedarf aus der Sicht einer etwas besonderen Nutzergruppe
Chiocchetti E (2019)
Presentation/Speech

Conference: Workshop NMT-Diagnose | Hildesheim | 12.12.2019 - 12.12.2019

http://hdl.handle.net/10863/12453
Adapting machine translation for under-resourced languages: a first attempt for institutional German in South Tyrol
De Camillis F, Contarino AG (2021)
Presentation/Speech

Conference: PaCor 2021 | Vitoria-Gasteiz | 23.6.2021 - 25.6.2021

https://hdl.handle.net/10863/17781
Project Team
1 - 4

Projects

1 - 9
Project

ITACA

Coherence in academic Italian

Duration: September 2020 - July 2021Funding:
Provincial P.-L.P. 14. Research projects (Province BZ funding /Project)

view all

Institute's Projects

Institute
Eurac Research logo

Eurac Research is a private research center based in Bolzano (South Tyrol) with researchers from a wide variety of scientific fields who come from all over the globe. Together, through scientific knowledge and research, they share the goal of shaping the future.

What we do

Our research addresses the greatest challenges facing us in the future: people need health, energy, well-functioning political and social systems and an intact environment. These are complex questions, and we are seeking the answers in the interaction between many different disciplines. In so doing, our research work embraces three major themes: regions fit for living in, diversity as a life-enhancing feature, a healthy society.

Great Place To Work

In order to give you a better service this site uses cookies. Additionally third party cookies are used. By continuing to browse the site you are agreeing to our use of cookies.

Privacy Policy