Strengthening the future of the Welsh language

laptop

The Welsh National Language Technologies Portal is provided by the Language Technologies Unit, Bangor University.

The Portal aims to be a one-stop shop to provide information of relevant resources and events, funded mainly by the Welsh Government.

computer

Resources for everyone

Ready-made products aimed at anyone who wishes to use Welsh Language Technologies, including Macsen, Y Trawsgrifiwr and App Dictionaries.

Accessibility

Resources to facilitate and promote accessibility including a screen reading program (NVDA), and bilingual synthetic voices.

github logo

Resources for developers

Resources aimed at software companies, researchers, hackers, enthusiastic volunteers as well as Welsh coding clubs.

Academic publications

Research into all aspects of Language Technologies, such as speech recognition, text-to-speech, artificial intelligence and much more.

Language technologies for all

macsen

Language Technologies include all activities where computers and electronic devices engage with human languages.

This can include speech recognition technology, text-to-speech, machine translation, natural language processing (NLP) and artificial intelligence (AI).

One resource that covers all these elements is the Welsh digital personal assistant, Macsen. It’s similar to Alexa or Google Assistant but works as an app… and it’s in Welsh!

macsen listens to the user and plays music

Resources for developers

docker, github, and European language grid logo
docker, github, and European language grid logo

The Welsh National Language Technologies Portal contains a host of resources aimed at software companies, researchers, hackers, enthusiastic volunteers as well as Welsh coding clubs.

All the documentation resources, examples and tutorials explaining the use of our product are located on GitHub.

The intention is to provide the resources as ‘building blocks’, open and free, in order to enable advanced and full Welsh language support within any finished digital product.

Academic publications

Research-led development of Language Technology resources is essential in order to promote the Welsh language as a living, modern language that looks towards the future.

The impact has extended beyond Wales, influencing the digital language equality road map internationally and influencing practice globally.

Language Report Welsh

Prys, D., Watkins, G. (2023). Language Report Welsh. In: Rehm, G., Way, A. (eds) European Language Equality. Cognitive Technologies. Springer, Cham.

European Language Equality Report on the Welsh Language

Prys, Delyth; Watkins, Gareth; Ghazzali, Stefano. European Language Equality Report on the Welsh Language. ELE Consortium, Adapt Centre, Dublin.

Evaluation of Three Welsh Language POS Taggers

Prys, Gruffudd & Watkins, Gareth. Evaluation of Three Welsh Language POS Taggers pp 33-39. In Proceedings of the 4th Celtic Language Technology Workshop within LREC eds. Theodorus Fransen, William Lamb & Delyth Prys. ELRA, Marseille.

Development and Evaluation of Speech Resources for the Welsh Language

Jones, Dewi Bryn. Development and Evaluation of Speech Resources for the Welsh Language pp52-59. In Proceedings of the 4th Celtic Language Technology Workshop within LREC eds. Theodorus Fransen, William Lamb & Delyth Prys. ELRA, Marseille.

An Open Source, Bilingual Welsh-to-English Text to Speech Corpus

Russel, Stephen; Jones, Dewi Bryn & Prys, Delyth. An Open Source, Bilingual Welsh-to-English Text to Speech Corpus pp104-109. In Proceedings of the 4th Celtic Language Technology Workshop within LREC eds. Theodorus Fransen, William Lamb & Delyth Prys. Marseille.

The Dawn of the Human-Machine Era

Sayers, Dave; Sousa-Silva, Rui; Höhn, Sviatlana; Ahmedi, Lule; Allkivi-Metsoja, Kais et al. 2021. The Dawn of the Human-Machine Era: A forecast of new and emerging language technologies. University of Jyväskylä.

Modelau Cyfrifiadurol ar gyfer Prosesu Lleferydd Cymraeg

Marshall. I. 2021. Modelau Cyfrifiadurol ar gyfer Prosesu Lleferydd Cymraeg.

Language and Technology in Wales: Volume I

Prys, D (ed.), 2021, Language and Technology in Wales: Volume I. Bangor University, Bangor.

Language and Technology in Wales: Volume II

Watkins, G (ed.), 2024, Language and Technology in Wales: Volume II. Bangor University, Bangor.

Coherent Planning for Language Technology Developments and Language Revitalization

Prys, D. Jones, D.B. & Prys, G. Coherent Planning for Language Technology Developments and Language Revitalization. In Adda, Giles et al. (eds.) LT4All Proceedings. ELRA, Paris. (p 367 – 370).

Term formation in Welsh

Prys, D, Andrews, T. & Prys, G. Term formation in Welsh: Problems and solutions. In Brač, Ivana; Ostroški Anić, Ana (eds.). Svijet od riječi. Terminološki i leksikografski ogledi. Institute of Croatian Language and Linguistics. Zagreb (pages 159 – 184).

Macsen

Jones, D.B. Macsen: A Voice Assistant for Speakers of a Lesser Resourced Language Paper in LREC 2020 SLTU-CCURL Workshop (pages 194-201).

Adapting a Welsh Terminology Tool to Develop a Cornish Dictionary

Prys, D. Adapting a Welsh Terminology Tool to Develop a Cornish Dictionary. Paper in LREC 2020 SLTU-CCURL Workshop (pages 235-239).

Planning for Language Technology Development and Language Revitalization in Wales

Prys, D.; Jones, D.B. & Prys, G. Planning for Language Technology Development and Language Revitalization in Wales. Proceedings of the Language Technologies for All (LT4All) UNESCO Conference, Paris, ELRA 2019 tt 367-370.

Embedding English to Welsh MT in a Private Company

Prys, M. & Jones D. B. Embedding English to Welsh MT in a Private Company Proceedings of the Celtic Language Technology Workshop. European Association for Machine Translation.

Proceedings of the Celtic Language Technology Workshop

Lynn, T; Prys, D; Batchelor, C; Tyers, F. (editors) Proceedings of the Celtic Language Technology Workshop. European Association for Machine Translation.

Crowdsourcing the Paldaruo Speech Corpus of Welsh for Speech Technology

Cooper, S; Jones, D.B & Prys, D. Crowdsourcing the Paldaruo Speech Corpus of Welsh for Speech Technology: in a special edition on Computational Linguistics for Low Resource Languages, Information, 2019. 10, 247.

A roundtable discussion to promote a strategic vision for Celtic Language Technologies.

Prys, D & Williams, I. A roundtable discussion to promote a strategic vision for Celtic Language Technologies. Roundtable discussion at the Celtic Congress at Bangor 2019.

Llawlyfr Technolegau Iaith

Jones, D.B; Pry,s D; Prys, M; Prys, G

Gathering Data for Speech Technology in the Welsh Language

Prys, D. & Jones, D.B. Gathering Data for Speech Technology in the Welsh Language: A Case Study : Paper in LREC 2018 CCURL Workshop (pages 56-61)

National Language Technologies Portals for LRLs

Prys, D. & Jones, D.B. National Language Technologies Portals for LRLs: a Case Study Lecture Notes in Artificial Intelligence. Springer.

Using LT tools in classroom and coding club activities to help LRLs

Prys, D., Jones, D.B & S. Ghazzali Using LT tools in classroom and coding club activities to help LRLs Language Technologies in Support of Less-Resourced Languages, (LRL 2017) 9 November 2017, Poznan, Poland

Facilitating the Multilingual Single Digital Market

Jones, D.B., Prys, D., Ghazzali, S. and Robertson, P. Facilitating the Multilingual Single Digital Market: Case Studies in Software Containerization of Language Technologies. Proceedings of META-FORUM 2016, Lisbon.

Vocab

Jones, D.B., Prys, G. and Prys, D. Vocab: a dictionary plugin for websites. Proceeding of the Second Celtic Language Technology Workshop, TALN 2016. Paris.

Cysill Ar-lein

Delyth Prys and Gruffudd Prys and Dewi Bryn Jones. Cysill Ar-lein: A Corpus of Written Contemporary Welsh Compiled from an On-line Spelling and Grammar Checker. Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016) Portoroz, Slovenia.

Reprinting scholarly works a e-books for less-resourced languages

Prys, D., Roberts, M. and Prys, G. 2016 Reprinting scholarly works a e-books for less-resourced languages. p74-79 Proceedings of the LREC 2016 Workshop “CCURL 2016 – Towards an Alliance for Digital Language Diversity”, Claudia Soria, Laurette Pretorius, Thierry Declerck, Joseph Mariani, Kevin Scannell, Eveline Wandl-Vogt.

Building Intelligent Digitial Assistants for Speakers of a Lesser-Resourced Language

Jones, D.B. and Cooper, S. 2016 Building Intelligent Digitial Assistants for Speakers of a Lesser-Resourced Language. p74-79 Proceedings of the LREC 2016 Workshop “CCURL 2016 – Towards an Alliance for Digital Language Diversity”, Claudia Soria, Laurette Pretorius, Thierry Declerck, Joseph Mariani, Kevin Scannell, Eveline Wandl-Vogt.

Terminology Standardization in Education and the Construction of Resources

Andrews, T. and Prys, G. 2016. Terminology Standardization in Education and the Construction of Resources: The Welsh Experience. Educational Sciences Vol 6, Issue 1. MDPI, Basel.

National Language Technology Portals for LRLs

Prys, D., and Jones D. B. 2016. National Language Technology Portals for LRLs: A Case Study. Language Technologies in Support of Less-Resourced Languages, (LRL 2015) 28 November 2015, Poznan, Poland

A taste of the resources

The WelshNational Language Technologies Portal is an extensive collection of Welsh technological resources.

These resources are aimed at software companies, researchers, hackers, enthusiastic volunteers as well as Welsh coding clubs.

Macsen

A Welsh personal digital assistant similar to Alexa. Available online and as an app on iOS and Android devices.

Synthetic voices

A collection of bilingual synthetic voices, Welsh and English.

green logo

Localization resources

Resources for translating software interface texts, converting units of time, money etc.

API services

An API services center that provides a range of online language technology services.

green logo

NVDA

Synthetic voice for screen reader software.

Trawsgrifiwr

A software program that transcribes Welsh speech into text, availale online and useful for creating video subtitles.

green logo

Aligner

A program that allows alignment between Welsh and English texts.

green logo

Machine translation

English > Welsh machine translation tools that use modern neural technology to translate texts.

vocab logo

Plug-ins

Plugins available for installation on your website to support the use of the Welsh language.

green logo

Ap Geiriaduron

Ap Geiriaduron is a Welsh-English, English-Welsh dictionary.

Stronger together

Wales with people's faces and connections
Wales with people's faces and connections

Ensuring a close connection with the world of business, industry and public services is crucial to our vision.

Knowledge Transfer Partnerships (KTP) are one way of facilitating the transfer of academic knowledge and expertise to ‘real’ world projects.

We have held many such partnerships in the past, with small and large companies, from Wales and beyond and are keen to continue bridging the gap between academia and industry.

Ready to contribute?

robot saying data
In order to continue to improve our resources, we need a large amount of data.

If you wish to be part of the Welsh digital revolution, you can share your voice or validate sentences through the Common Voice website. Or if you have audio recordings, whether podcasts, TV programs or videos you would be happy to share and which are free of copyright, please contact us!

Contact us