@inproceedings{doyle-mccrae-2024-developing,
title = "Developing a Part-of-speech Tagger for Diplomatically Edited {O}ld {I}rish Text",
author = "Doyle, Adrian and
McCrae, John P.",
editor = "Sprugnoli, Rachele and
Passarotti, Marco",
booktitle = "Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lt4hala-1.2",
pages = "11--21",
abstract = "POS-tagging is typically considered a fundamental text preprocessing task, with a variety of downstream NLP tasks and techniques being dependent on the availability of POS-tagged corpora. As such, POS-taggers are important precursors to further NLP tasks, and their accuracy can impact the potential accuracy of these dependent tasks. While a variety of POS-tagging methods have been developed which work well with modern languages, historical languages present orthographic and editorial challenges which require special attention. The effectiveness of POS-taggers developed for modern languages is reduced when applied to Old Irish, with its comparatively complex orthography and morphology. This paper examines some of the obstacles to POS-tagging Old Irish text, and shows that inconsistencies between extant annotated corpora reduce the quantity of data available for use in training POS-taggers. The development of a multi-layer neural network model for POS-tagging Old Irish text is described, and an experiment is detailed which demonstrates that this model outperforms a variety of off-the-shelf POS-taggers. Moreover, this model sets a new benchmark for POS-tagging diplomatically edited Old Irish text.",
}
Markdown (Informal)
[Developing a Part-of-speech Tagger for Diplomatically Edited Old Irish Text](https://aclanthology.org/2024.lt4hala-1.2) (Doyle & McCrae, LT4HALA-WS 2024)
ACL