Language Technology and Language Revitalization in Wales

The Unit for Linguistic Data at the Insight SFI Research Centre for Data Analytics / Data Science Institute, National University of Ireland Galway is delighted to welcome Prof Delyth Prys of the University of Bangor (Wales) to be the next speaker in our seminar series. As this seminar will be held on International Mother Language Day, Prof Prys will highlight aspects of language revitalization and digital language equality in the context of the Welsh language, in addition to providing an overview of recent developments in speech and language technology for this under-resourced Celtic language.

Abstract:

This talk will present the UniMorph project, an attempt to create a universal (cross-lingual) annotation schema. UniMorph allows an inflected word from any language to be defined by its lexical meaning, typically carried by the lemma, and a bundle of universal morphological features defined by the schema. Since 2016, the UniMorph database has been gradually developed and updated with new languages, and SIGMORPHON shared tasks served as a platform to compare computational models of inflectional mThis talk will examine recent development of speech and language technology, translation technology and conversational AI for Welsh in the context of the current Government Welsh Language Technology Action Plan. It will detail new resources, tools, services and products created for Welsh and published in GitHub and the ELG under open permissive licences, the philosophy of open source publishing as an aid to language revitalization and economic recovery in peripheral regions, and the impact of this philosophy on the drive for digital language equality in Europe.

About the Speaker:

Delyth Prys is Professor in the School of Arts, Culture of Language and Head of Language Technologies at Bangor University. She has been engaged in Terminology Standardization at BU since 1993, and since 2001 has led a mixed team of linguists and computer scientists in researching and developing innovative language technologies for less-resourced languages. The main focus of her work is Welsh, together with the wider Celtic family of languages, but she also investigates innovative solutions to data sparsity and the use of language technologies for language revitalization in general.

Professor Prys is a member of numerous Welsh Government committees, a member of BSI/TS1 and convenor of ISO/TC37 working group on socioterminology. In 2018 she won the Womanspire ‘Building Wales’ Award for Science and Technology, and in 2019 the UK’s RCSLT’s Giving Voice Award.

Host:

The seminar series is led by the Cardamom project team. The Cardamom project aims to close the resource gap for minority and under-resourced languages using deep-learning-based natural language processing (NLP) and exploiting similarities of closely related languages. The project further extends this idea to historical languages, which can be considered closely related to their modern form. It aims to provide NLP through both space and time for languages that current approaches have ignored.