Python Ireland August 2024 Meetup

Taking the ‘-Deoir’ out of ‘Taighdeoir’: Creating a Substring Search Tool for the Irish Language in Python

Deoir; tear
-oir; suffix, ‘-er’
Taighdeoir; researcher

The Irish language has a number of comprehensive and up-to-date online learning tools, databases, and dictionaries. However, there was no way for Irish learners or users to search for specific substrings, despite their importance in Irish to denote number (singular or plural), gender, case, and noun declension (how a noun is conjugated or pluralised).

This talk will discuss the process of creating an application in Python to remedy this problem, and will present our solution, Míreadóir, a search tool for Irish-language substrings. It is hoped that this tool will benefit language teachers and learners, and every-day Irish users. With substrings also encompassing suffixes, it is also possible that this tool could act as a rhyming dictionary or support in creative writing.

The talk will consider the collaboration between an Irish-language translator and scholar, and a data scientist and Irish-language learner; the implications of machine learning on language learning and translation; and offer a beginner-friendly discussion on web scraping, string processing, and creating a bilingual front-end for a data science project.

Mykalin Jones is a data scientist, curriculum writer, instructor, and passionate learner of the Irish language.
Ellen Corbett is a PhD researcher, translator, and frequent user of Irish dictionaries.

Big thanks to our sponsor for this edition, XtremePush