The aim of GoURMET is to use and improve neural machine translation for low-resource language pairs and domains.
Why? – Because machine translation works very well in situations where there are millions of translated sentences for training models. For low-resourced language pairs, however, the quality of translation is barely, if at all, usable. For more info, see “GoURMET in a nutshell“
GoURMET has five objectives
- Advancing low-resource deep learning for natural language applications
- Develop a high-quality machine translation for low-resource language pairs and domains
- Develop tools for media analysts and journalists
- Create a sustainable and maintainable platform and services
- Inform stakeholders and user group of project results
Also see the three Use Cases we focus on (content creation, media monitoring, analysing business news).
Our Open Source Collection
Start to interact! Here you find our GoURMET Translate Tool and our Data, Model and Software Releases. As part of GoURMET’s efforts to increase resources and tools available for low-resource machine translation, we release the corpora and software created during the project.
News
Looking for news around the project? Also visit the blog section and read our featured post: Susie Coleman from the BBC on Building the GoURMET Translation Tool for low-resource languages.