Machine Translation

, Volume 18, Issue 3, pp 173–193 | Cite as

Design, Implementation and Evaluation of an Inflectional Morphology Finite State Transducer for Irish

  • Uí Dhonnchadha
  • Caoilfhionn Nic Pháidín
  • Josef Van Genabith


Minority languages must endeavour to keep up with and avail of language technology advances if they are to prosper in the modern world. Finite state technology is mature, stable and robust. It is scalable and has been applied successfully in many areas of linguistic processing, notably in phonology, morphology and syntax. In this paper, the design, implementation and evaluation of a morphological analyser and generator for Irish using finite state transducers is described. In order to produce a high-quality linguistic resource for NLP applications, a complete set of inflectional morphological rules for Irish is handcrafted, as is the initial test lexicon. The lexicon is then further populated semi-automatically using both electronic and printed lexical resources. Currently we achieve coverage of 89% on unrestricted text. Finally we discuss a number of methodological issues in the design of NLP resources for minority languages.


computational morphology finite state transducer Irish Celtic languages minority languages 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. An Roinn Oideachais: 1986, Foclóir Póca English–Irish/Irish–English Dictionary [Pocket dictionary], Bailé Atha Cliath: An Gúum.Google Scholar
  2. Beesley, K., Karttunen, L. 2003Finite State Morphology: Xerox Tools and TechniquesCSLIStanford, CAGoogle Scholar
  3. Bráithre Críostaí: 1999, Graiméar Gaeilge na mBráithre Críostaí [The Christian Brothers’ Irish Grammar], 2nd ed., Baile Átha Cliath: An Gúum.Google Scholar
  4. Campbell, G.L. 2000Compendium of the World’s Languages2RoutledgeLondonGoogle Scholar
  5. Christian Brothers1988New Irish GrammarFallonsDublinGoogle Scholar
  6. Daciuk, J.: n.d., Finite state utilities. (consulted 1/10/2003).Google Scholar
  7. Fife, J. 1993‘Introduction’Ball, M.J.Fife, J. eds. The Celtic Languages.RoutledgeLondon325Google Scholar
  8. ITÉ (Institiúid Teangeolaíochta Éireann): n.d., Corpas Náisiúnta na Gaeilge, [National Corpus of Irish]. (consulted 1/10/2003).Google Scholar
  9. Mohri, M., F. C. N. Pereira and M. D. Riley: 2003, AT&T FSM LibraryTM– Finite-State Machine Library, (consulted 1/10/2003).Google Scholar
  10. Ó Cuív, B. 1987‘Sandhi phenomena in Irish’Andersen, H. eds. Sandhi Phenomena in the Languages of EuropeMouton de GruyterBerlin395414Google Scholar
  11. Ó Droighneáin M. (1991). An Sloinnteoir Gaeilge agus an tAinmneoir [Irish Surnames and Names]. Baile Átha Cliath: Coiscéim.Google Scholar
  12. Ó Siochfhradha, N.: 1998, Foclóir Gaeilge/Béarla – Béarla/Gaeilge [Irish/English – English/Irish Dictionary], Baile Átha Cliath: An Comhlacht Oideachais, Cló Thalbóid.Google Scholar
  13. Rannóg an Aistriúcháin: 1958, Gramadach na Gaeilge agus Litriú na Gaeilge: An Caighdeán Oifigiúuil [Irish Grammar and Irish Spelling: The Official Standard]. Baile Átha Cliath: Oifig an tSoláthair.Google Scholar
  14. Russell, P. 1995An Introduction to the Celtic LanguagesLongmanLondonGoogle Scholar
  15. SIL International: 2004, PC-KIMMO, A morphological parser. (consulted 1/10/2003).Google Scholar
  16. Stenson, N.: 1981, Studies in Irish Syntax, Tübingen: Gunter Narr.Google Scholar
  17. Uý Dhonnchadha, E.: 2003, ‘Finite-State Morphology and Irish’, in Proceedings of the Workshop on Finite-State Methods in Natural Language Processing, 10th Conference of the European Chapter of the Association for Computational Linguistics, Budapest, Hungary, pp. 43–49.Google Scholar

Copyright information

© Springer 2005

Authors and Affiliations

  • Uí Dhonnchadha
    • 1
  • Caoilfhionn Nic Pháidín
    • 2
  • Josef Van Genabith
    • 3
  1. 1.Institiúid Teangeolaíochta ÉireannDublin 2Ireland
  2. 2.FiontarDublin City UniversityDublin 9Ireland
  3. 3.National Centre for Language Technology, School of ComputingDublin City UniversityDublin 9Ireland

Personalised recommendations