@inproceedings{lameris-stymne-2021-whits,
title = "Whit{'}s the Richt Pairt o Speech: {P}o{S} tagging for {S}cots",
author = "Lameris, Harm and
Stymne, Sara",
editor = {Zampieri, Marcos and
Nakov, Preslav and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Scherrer, Yves and
Jauhiainen, Tommi},
booktitle = "Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects",
month = apr,
year = "2021",
address = "Kiyv, Ukraine",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.vardial-1.5",
pages = "39--48",
abstract = "In this paper we explore PoS tagging for the Scots language. Scots is spoken in Scotland and Northern Ireland, and is closely related to English. As no linguistically annotated Scots data were available, we manually PoS tagged a small set that is used for evaluation and training. We use English as a transfer language to examine zero-shot transfer and transfer learning methods. We find that training on a very small amount of Scots data was superior to zero-shot transfer from English. Combining the Scots and English data led to further improvements, with a concatenation method giving the best results. We also compared the use of two different English treebanks and found that a treebank containing web data was superior in the zero-shot setting, while it was outperformed by a treebank containing a mix of genres when combined with Scots data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lameris-stymne-2021-whits">
<titleInfo>
<title>Whit’s the Richt Pairt o Speech: PoS tagging for Scots</title>
</titleInfo>
<name type="personal">
<namePart type="given">Harm</namePart>
<namePart type="family">Lameris</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Stymne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</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">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommi</namePart>
<namePart type="family">Jauhiainen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kiyv, Ukraine</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we explore PoS tagging for the Scots language. Scots is spoken in Scotland and Northern Ireland, and is closely related to English. As no linguistically annotated Scots data were available, we manually PoS tagged a small set that is used for evaluation and training. We use English as a transfer language to examine zero-shot transfer and transfer learning methods. We find that training on a very small amount of Scots data was superior to zero-shot transfer from English. Combining the Scots and English data led to further improvements, with a concatenation method giving the best results. We also compared the use of two different English treebanks and found that a treebank containing web data was superior in the zero-shot setting, while it was outperformed by a treebank containing a mix of genres when combined with Scots data.</abstract>
<identifier type="citekey">lameris-stymne-2021-whits</identifier>
<location>
<url>https://aclanthology.org/2021.vardial-1.5</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>39</start>
<end>48</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Whit’s the Richt Pairt o Speech: PoS tagging for Scots
%A Lameris, Harm
%A Stymne, Sara
%Y Zampieri, Marcos
%Y Nakov, Preslav
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Scherrer, Yves
%Y Jauhiainen, Tommi
%S Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kiyv, Ukraine
%F lameris-stymne-2021-whits
%X In this paper we explore PoS tagging for the Scots language. Scots is spoken in Scotland and Northern Ireland, and is closely related to English. As no linguistically annotated Scots data were available, we manually PoS tagged a small set that is used for evaluation and training. We use English as a transfer language to examine zero-shot transfer and transfer learning methods. We find that training on a very small amount of Scots data was superior to zero-shot transfer from English. Combining the Scots and English data led to further improvements, with a concatenation method giving the best results. We also compared the use of two different English treebanks and found that a treebank containing web data was superior in the zero-shot setting, while it was outperformed by a treebank containing a mix of genres when combined with Scots data.
%U https://aclanthology.org/2021.vardial-1.5
%P 39-48
Markdown (Informal)
[Whit’s the Richt Pairt o Speech: PoS tagging for Scots](https://aclanthology.org/2021.vardial-1.5) (Lameris & Stymne, VarDial 2021)
ACL