Lynn, Teresa (2012) Medieval Irish and computational linguistics. Australian Celtic journal, 10 . pp. 13-27. ISSN 1030-2611
Abstract
This paper will consider the application of some NLP (Natural
Language Processing) techniques to Medieval Irish texts to
provide an alternative perspective on linguistic analyses of such
texts. Using Táin Bó Fraích as a case study, I present the
outcome of some preliminary experiments. The pilot study starts
with the creation of an annotated lexicon as a basis of automated
text analysis. Linguistic features such as part of speech
information are recorded in a machine-readable representation to
assist with subsequent linguistic analysis of this well-studied
text. Using CELT’s electronic version of Meid’s 1974 edition, I
conduct both statistical and linguistic analyses of textual features
such as sentence structure, lexical frequency and grammatical
types. I use the results of this analysis to raise some tentative
suggestions regarding Táin Bó Fraích, and in particular the
frequently noted relationship between the two distinct sections.
On this basis I hope to make some suggestions about the
potential usefulness of applying some NLP techniques to
Medieval Irish.
Metadata
Item Type: | Article (Published) |
---|---|
Refereed: | Yes |
Subjects: | Computer Science > Machine translating Humanities > Irish language Humanities > Linguistics |
DCU Faculties and Centres: | DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing Research Institutes and Centres > ADAPT |
Publisher: | Celtic Council of Australia and University of Sydney's Celtic Studies Foundation. |
Copyright Information: | © 2012 The Celtic Council of Australia and the author. |
Use License: | This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License |
ID Code: | 23600 |
Deposited On: | 26 Jul 2019 11:37 by Thomas Murtagh . Last Modified 26 Jul 2019 11:37 |
Documents
Full text available as:
Preview |
PDF
- Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
389kB |
Downloads
Downloads
Downloads per month over past year
Archive Staff Only: edit this record