Funding of over €350,000 for two technology projects aimed at supporting the Irish language was announced by Minister of State for Sport and the Gaeltacht, Jack Chambers today at DCU. The successful projects, GaelTech and the National Relay Station, are led by the SFI ADAPT Centre for AI Driven Digital Content Technology at DCU.
Irish is an official EU minority language and has been classified by UNESCO as ‘definitely endangered’. The development of technologies usually focuses on supporting the major languages of the world such as English, Chinese and Spanish. New digital content tools allow minority languages to be supported in the same way through systems that can process and understand the language and hence help minority language speakers. The two technology projects underway at the ADAPT Centre in DCU aim to support the Irish language and culture long-term and help integrate it into wider society.
GaelTech is a project focused on the development of natural language processing tools and resources for the Irish language. It aims to provide training for a new generation of Irish language technologists, and to develop a crucial set of resources to mitigate the risk of digital extinction of the Irish language.
Speaking about the impact the funding will have on securing the future of the Irish language, lead researcher Dr Teresa Lynn said: “In the world of AI, investing in language technology is regarded as a step towards future-proofing a language against the risk of digital extinction. As technology becomes more prevalent in our daily lives, we will need to ensure continued digital use of our minority languages, along with the necessary upskilling of those who can make this happen. For this reason, we greatly welcome the latest announcement of the Irish Government’s continued support for Irish language technology.”
The research and development project, which has been running since 2017, will be extended by two years allowing researchers assess the effect of automatic Irish multiword expression processing on user applications such as machine translation (MT), and develop a tool to understand Irish language text on social media while exploring the unique interaction between the English and Irish languages on Twitter.
In recent times social networks have increased their language scope allowing users the opportunity to express themselves in their own language while also providing simultaneous translations in languages other than their own. This activity highlights the potential engagement and stimulus for people when languages are supported digitally.
National Relay Station
The second project that will benefit from the funding is the National Relay Station (NRS). The NRS was the first platform to share bilingual language data nationally, and has been used by people working with the Irish language to upload language data for MT engine training to one central location. The NRS was developed by researchers at the ADAPT Centre through the EU-funded European Language Resource Infrastructure (ELRI) project (2017-2019). Following on from ELRI, the PRINCIPLE project coordinated in DCU by ADAPT Deputy Director, Professor Andy Way, has continued to collect further amounts of English-Irish training data to improve MT quality.
This additional government funding will mean that the NRS can continue to be hosted by DCU until the end of 2022. The existence of this central repository for English/Irish translation data will continue to support the development of translation technology for the Irish language at a national level, whilst also continuing to improve the quality of Irish-language translations from the European Commission’s MT system, eTranslation.
Speaking about the support, Professor Way said: “Today’s MT systems all rely on high-quality parallel data – the original sentence and its translation – to ensure good quality translations. The MT team in ADAPT at DCU has for a long time been engaged with various Government departments to help provide a range of public documents in Irish for citizens who prefer to communicate through this language, rather than be forced to access information through English. Now that the NRS is secured for the near future, the data collections established in ELRI and PRINCIPLE can continue, so that the MT systems that we build continue to improve. With the EU’s Irish-language derogation coming to an end at the end of this year’ time, this investment by the Government is very timely indeed”.
The Government funding will enable both GaelTech and the National Relay Station to continue their research and development for the next two years.
Our partners @ait_research @TUS_ie will be an #AI hub for our #DiscussAI initiative. Join the #scienceweek event this Nov 11th. More info: http://thinkins.adaptcentre.ie/events/ @CaitMordan @atimcluster
Read more: https://bit.ly/30GkhUe