@inproceedings{scannell-2022-diachronic,
title = "Diachronic Parsing of Pre-Standard {I}rish",
author = "Scannell, Kevin",
editor = "Fransen, Theodorus and
Lamb, William and
Prys, Delyth",
booktitle = "Proceedings of the 4th Celtic Language Technology Workshop within LREC2022",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.cltw-1.2",
pages = "7--13",
abstract = "Irish underwent a major spelling standardization in the 1940{'}s and 1950{'}s, and as a result it can be challenging to apply language technologies designed for the modern language to older, {``}pre-standard{''} texts. Lemmatization, tagging, and parsing of these pre-standard texts play an important role in a number of applications, including the lexicographical work on Focl{\'o}ir Stairi{\'u}il na Gaeilge, a historical dictionary of Irish covering the period from 1600 to the present. We have two main goals in this paper. First, we introduce a small benchmark corpus containing just over 3800 words, annotated according to the Universal Dependencies guidelines and covering a range of dialects and time periods since 1600. Second, we establish baselines for lemmatization, tagging, and dependency parsing on this corpus by experimenting with a variety of machine learning approaches.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scannell-2022-diachronic">
<titleInfo>
<title>Diachronic Parsing of Pre-Standard Irish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Scannell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Celtic Language Technology Workshop within LREC2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Theodorus</namePart>
<namePart type="family">Fransen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Lamb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Delyth</namePart>
<namePart type="family">Prys</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Irish underwent a major spelling standardization in the 1940’s and 1950’s, and as a result it can be challenging to apply language technologies designed for the modern language to older, “pre-standard” texts. Lemmatization, tagging, and parsing of these pre-standard texts play an important role in a number of applications, including the lexicographical work on Foclóir Stairiúil na Gaeilge, a historical dictionary of Irish covering the period from 1600 to the present. We have two main goals in this paper. First, we introduce a small benchmark corpus containing just over 3800 words, annotated according to the Universal Dependencies guidelines and covering a range of dialects and time periods since 1600. Second, we establish baselines for lemmatization, tagging, and dependency parsing on this corpus by experimenting with a variety of machine learning approaches.</abstract>
<identifier type="citekey">scannell-2022-diachronic</identifier>
<location>
<url>https://aclanthology.org/2022.cltw-1.2</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>7</start>
<end>13</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Diachronic Parsing of Pre-Standard Irish
%A Scannell, Kevin
%Y Fransen, Theodorus
%Y Lamb, William
%Y Prys, Delyth
%S Proceedings of the 4th Celtic Language Technology Workshop within LREC2022
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F scannell-2022-diachronic
%X Irish underwent a major spelling standardization in the 1940’s and 1950’s, and as a result it can be challenging to apply language technologies designed for the modern language to older, “pre-standard” texts. Lemmatization, tagging, and parsing of these pre-standard texts play an important role in a number of applications, including the lexicographical work on Foclóir Stairiúil na Gaeilge, a historical dictionary of Irish covering the period from 1600 to the present. We have two main goals in this paper. First, we introduce a small benchmark corpus containing just over 3800 words, annotated according to the Universal Dependencies guidelines and covering a range of dialects and time periods since 1600. Second, we establish baselines for lemmatization, tagging, and dependency parsing on this corpus by experimenting with a variety of machine learning approaches.
%U https://aclanthology.org/2022.cltw-1.2
%P 7-13
Markdown (Informal)
[Diachronic Parsing of Pre-Standard Irish](https://aclanthology.org/2022.cltw-1.2) (Scannell, CLTW 2022)
ACL
- Kevin Scannell. 2022. Diachronic Parsing of Pre-Standard Irish. In Proceedings of the 4th Celtic Language Technology Workshop within LREC2022, pages 7–13, Marseille, France. European Language Resources Association.