A machine translation service with post-editing

Machine translation

Luisa Tõlkebüroo OÜ is the biggest translation agency in Estonia. The company offers more than 50 services – including sworn translation, simultaneous and consecutive interpretation, layout work, machine translation and post-editing, subtitling and localisation.

Technical/scientific Challenge:

The company needed a custom-made machine translation system to reduce the time of translations.

Solution:

As the company had no previous experience neither in natural language processing nor in machine learning, they collaborated with the TartuNLP team. Training of the machine translation model was conducted by using University of Tartu HPC centre’s Rocket cluster. Once the models were trained, the company considered different options for deployment. Their initial plan was to invest in their own infrastructure but soon they realized that it would not be justified for their use case and the TartuNLP group deployed the models alongside other services in the cloud.  

Business impact:

Thanks to rapid advances in the technology and our extensive translation memory, the company is able to offer its customers machine translation service with post-editing in a range of language combinations and on a range of topics. The new service makes the company's service package more attractive, reduces costs and increases competitiveness in the market.

Benefits:

  • Neural machine translation systems were built for 4 language pairs and several text domains.

  • The company enjoyed lower deployment costs and did not have to worry about maintaining their own hardware.

  • The innovative translation tool helps to save valuable time and human resources.