New resources for Welsh communication infrastructure

During 2015-16, the Language Technologies Unit team, based at Canolfan Bedwyr, Bangor University, developed new resources to enable communication in Welsh with computers and digital devices. This is a technology which is becoming increasingly prevalent as the human voice is used more and more for question and answer systems on mobile phones and tablets, and voice control for such things as television sets, robots and dictation systems. If Welsh cannot be used in these environments, then the language will be excluded from the digital world and Welsh speakers will have no choice but to speak English with these devices.

In order to pave the way for new Welsh medium technologies, the Welsh government and S4C have funded the innovative Welsh Communications Infrastructure project at Bangor University. The project has produced a Welsh question and answer prototype, where a personal assistant “Macsen” is able to answer questions such as what is the news or weather, and has also created an alpha version of a Welsh transcribing system, together with the acoustic models, language models, and corpus of spoken Welsh used to assist in their creation.

Dewi Bryn Jones, the project’s main software developer, explained that:

“The intention is to give free access to these resources through the National Language Technologies Portal, so that software developers, major international corporations and small local companies, coding clubs, hackers and anyone interested in creating Welsh software, can develop them further within their own software. All the data, the source code, usage notes and other useful information is stored within Github, a web-based repository used extensively by developers. We will also be holding a session on these resources at the “Hacio’r Iaith” language hacking event at Cardiff on the 16th of April, and we are very much looking forward to it.”

One of the first people to be shown the ‘Macsen’ prototype was the Welsh First Minister, Carwyn Jones.

The First Minister said:

“I’m glad to see the Welsh Government’s support contributing to an important infrastructure project like this. In order for the Welsh language to continue to flourish as a contemporary language, it’s clear that it needs to adapt and contribute to as many elements of modern life as possible. Producing a wide range of technology and devices that are able to understand and communicate in Welsh is central to this.”

The system has also been shown to pupils at Ysgol Uwchradd Bodedern, on Anglesey, in a session with Dr Cynog Prys from the School of Social Sciences, Bangor University.

“The pupils loved it” he said. “In a world where technology is perceived to be something that belongs to the English language, it is very important that young people understand that it’s possible to have these devices using Welsh as well. It’s an important part of making sure that Welsh continues to flourish in the modern digital world.”

These resources will be placed on the National Language Technologies Portal’s website:, as well as in other repositories for developers.

Publication date: 18 March 2016