Edinburgh Research Explorer

Developing an automatic part-of-speech tagger for Scottish Gaelic

Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)

Related Edinburgh Organisations

Open Access permissions

Open

Documents

  • Download as Adobe PDF

    Rights statement: ©Danso, S., & Lamb, W. (2014). Developing an Automatic Part-of-Speech Tagger for Scottish Gaelic. In J. John, L. Theresa, W. Monica, & B. Ó Raghallaigh (Eds.), Proceedings of the Celtic Technology Workshop (CLTW 2014): A Workshop of the 25th International Conference on Computational Linguistics (COLING 2014) August 23, 2014 Dublin, Ireland. (Vol. 1, pp. 1-5). [1]

    Final published version, 242 KB, PDF-document

    Licence: Creative Commons: Attribution (CC-BY)

Original languageEnglish
Title of host publicationProceedings of the Celtic Technology Workshop (CLTW 2014)
Subtitle of host publicationA Workshop of the 25th International Conference on Computational Linguistics (COLING 2014) August 23, 2014 Dublin, Ireland
EditorsJohn Judge, Theresa Lynn, Monica Ward, Ó Raghallaigh Brian
Pages1-5
Number of pages5
Volume1
ISBN (Electronic)978-1-873769-32-4
Publication statusPublished - 23 Aug 2014
EventCeltic Language Technology Workshop (CLTW 2014) - Dublin, United Kingdom
Duration: 23 Aug 2014 → …

Workshop

WorkshopCeltic Language Technology Workshop (CLTW 2014)
CountryUnited Kingdom
CityDublin
Period23/08/14 → …

Abstract

This paper describes an on-going project that seeks to develop the first automatic PoS tagger for Scottish Gaelic. Adapting the PAROLE tagset for Irish, we manually re-tagged a preexisting 86k token corpus of Scottish Gaelic. A double-verified subset of 13.5k tokens was used to instantiate eight statistical taggers and verify their accuracy, via a randomly assigned hold-out sample. An accuracy level of 76.6% was achieved using a Brill bigram tagger. We provide an overview of the project’s methodology, interim results and future directions.

Event

Celtic Language Technology Workshop (CLTW 2014)

23/08/14 → …

Dublin, United Kingdom

Event: Workshop

Download statistics

No data available

ID: 17307732