@inproceedings{cassidy-etal-2022-twittirish,
title = "{T}witt{I}rish: A {U}niversal {D}ependencies Treebank of Tweets in {M}odern {I}rish",
author = "Cassidy, Lauren and
Lynn, Teresa and
Barry, James and
Foster, Jennifer",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.473",
doi = "10.18653/v1/2022.acl-long.473",
pages = "6869--6884",
abstract = "Modern Irish is a minority language lacking sufficient computational resources for the task of accurate automatic syntactic parsing of user-generated content such as tweets. Although language technology for the Irish language has been developing in recent years, these tools tend to perform poorly on user-generated content. As with other languages, the linguistic style observed in Irish tweets differs, in terms of orthography, lexicon, and syntax, from that of standard texts more commonly used for the development of language models and parsers. We release the first Universal Dependencies treebank of Irish tweets, facilitating natural language processing of user-generated content in Irish. In this paper, we explore the differences between Irish tweets and standard Irish text, and the challenges associated with dependency parsing of Irish tweets. We describe our bootstrapping method of treebank development and report on preliminary parsing experiments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cassidy-etal-2022-twittirish">
<titleInfo>
<title>TwittIrish: A Universal Dependencies Treebank of Tweets in Modern Irish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lauren</namePart>
<namePart type="family">Cassidy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teresa</namePart>
<namePart type="family">Lynn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Barry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Modern Irish is a minority language lacking sufficient computational resources for the task of accurate automatic syntactic parsing of user-generated content such as tweets. Although language technology for the Irish language has been developing in recent years, these tools tend to perform poorly on user-generated content. As with other languages, the linguistic style observed in Irish tweets differs, in terms of orthography, lexicon, and syntax, from that of standard texts more commonly used for the development of language models and parsers. We release the first Universal Dependencies treebank of Irish tweets, facilitating natural language processing of user-generated content in Irish. In this paper, we explore the differences between Irish tweets and standard Irish text, and the challenges associated with dependency parsing of Irish tweets. We describe our bootstrapping method of treebank development and report on preliminary parsing experiments.</abstract>
<identifier type="citekey">cassidy-etal-2022-twittirish</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.473</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.473</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>6869</start>
<end>6884</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TwittIrish: A Universal Dependencies Treebank of Tweets in Modern Irish
%A Cassidy, Lauren
%A Lynn, Teresa
%A Barry, James
%A Foster, Jennifer
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F cassidy-etal-2022-twittirish
%X Modern Irish is a minority language lacking sufficient computational resources for the task of accurate automatic syntactic parsing of user-generated content such as tweets. Although language technology for the Irish language has been developing in recent years, these tools tend to perform poorly on user-generated content. As with other languages, the linguistic style observed in Irish tweets differs, in terms of orthography, lexicon, and syntax, from that of standard texts more commonly used for the development of language models and parsers. We release the first Universal Dependencies treebank of Irish tweets, facilitating natural language processing of user-generated content in Irish. In this paper, we explore the differences between Irish tweets and standard Irish text, and the challenges associated with dependency parsing of Irish tweets. We describe our bootstrapping method of treebank development and report on preliminary parsing experiments.
%R 10.18653/v1/2022.acl-long.473
%U https://aclanthology.org/2022.acl-long.473
%U https://doi.org/10.18653/v1/2022.acl-long.473
%P 6869-6884
Markdown (Informal)
[TwittIrish: A Universal Dependencies Treebank of Tweets in Modern Irish](https://aclanthology.org/2022.acl-long.473) (Cassidy et al., ACL 2022)
ACL