@inproceedings{wisniewski-yvon-2019-bad,
title = "{H}ow {B}ad are {P}o{S} {T}agger in {C}ross-{C}orpora {S}ettings? {E}valuating {A}nnotation {D}ivergence in the {UD} {P}roject.",
author = "Wisniewski, Guillaume and
Yvon, Fran{\c{c}}ois",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1019",
doi = "10.18653/v1/N19-1019",
pages = "218--227",
abstract = "The performance of Part-of-Speech tagging varies significantly across the treebanks of the Universal Dependencies project. This work points out that these variations may result from divergences between the annotation of train and test sets. We show how the annotation variation principle, introduced by Dickinson and Meurers (2003) to automatically detect errors in gold standard, can be used to identify inconsistencies between annotations; we also evaluate their impact on prediction performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wisniewski-yvon-2019-bad">
<titleInfo>
<title>How Bad are PoS Tagger in Cross-Corpora Settings? Evaluating Annotation Divergence in the UD Project.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Wisniewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Yvon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The performance of Part-of-Speech tagging varies significantly across the treebanks of the Universal Dependencies project. This work points out that these variations may result from divergences between the annotation of train and test sets. We show how the annotation variation principle, introduced by Dickinson and Meurers (2003) to automatically detect errors in gold standard, can be used to identify inconsistencies between annotations; we also evaluate their impact on prediction performance.</abstract>
<identifier type="citekey">wisniewski-yvon-2019-bad</identifier>
<identifier type="doi">10.18653/v1/N19-1019</identifier>
<location>
<url>https://aclanthology.org/N19-1019</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>218</start>
<end>227</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Bad are PoS Tagger in Cross-Corpora Settings? Evaluating Annotation Divergence in the UD Project.
%A Wisniewski, Guillaume
%A Yvon, François
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F wisniewski-yvon-2019-bad
%X The performance of Part-of-Speech tagging varies significantly across the treebanks of the Universal Dependencies project. This work points out that these variations may result from divergences between the annotation of train and test sets. We show how the annotation variation principle, introduced by Dickinson and Meurers (2003) to automatically detect errors in gold standard, can be used to identify inconsistencies between annotations; we also evaluate their impact on prediction performance.
%R 10.18653/v1/N19-1019
%U https://aclanthology.org/N19-1019
%U https://doi.org/10.18653/v1/N19-1019
%P 218-227
Markdown (Informal)
[How Bad are PoS Tagger in Cross-Corpora Settings? Evaluating Annotation Divergence in the UD Project.](https://aclanthology.org/N19-1019) (Wisniewski & Yvon, NAACL 2019)
ACL