@inproceedings{poesio-etal-2019-crowdsourced,
title = "A Crowdsourced Corpus of Multiple Judgments and Disagreement on Anaphoric Interpretation",
author = "Poesio, Massimo and
Chamberlain, Jon and
Paun, Silviu and
Yu, Juntao and
Uma, Alexandra and
Kruschwitz, Udo",
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/N19-1176",
doi = "10.18653/v1/N19-1176",
pages = "1778--1789",
abstract = "We present a corpus of anaphoric information (coreference) crowdsourced through a game-with-a-purpose. The corpus, containing annotations for about 108,000 markables, is one of the largest corpora for coreference for English, and one of the largest crowdsourced NLP corpora, but its main feature is the large number of judgments per markable: 20 on average, and over 2.2M in total. This characteristic makes the corpus a unique resource for the study of disagreements on anaphoric interpretation. A second distinctive feature is its rich annotation scheme, covering singletons, expletives, and split-antecedent plurals. Finally, the corpus also comes with labels inferred using a recently proposed probabilistic model of annotation for coreference. The labels are of high quality and make it possible to successfully train a state of the art coreference resolver, including training on singletons and non-referring expressions. The annotation model can also result in more than one label, or no label, being proposed for a markable, thus serving as a baseline method for automatically identifying ambiguous markables. A preliminary analysis of the results is presented.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="poesio-etal-2019-crowdsourced">
<titleInfo>
<title>A Crowdsourced Corpus of Multiple Judgments and Disagreement on Anaphoric Interpretation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Massimo</namePart>
<namePart type="family">Poesio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jon</namePart>
<namePart type="family">Chamberlain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Silviu</namePart>
<namePart type="family">Paun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juntao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Uma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Udo</namePart>
<namePart type="family">Kruschwitz</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>We present a corpus of anaphoric information (coreference) crowdsourced through a game-with-a-purpose. The corpus, containing annotations for about 108,000 markables, is one of the largest corpora for coreference for English, and one of the largest crowdsourced NLP corpora, but its main feature is the large number of judgments per markable: 20 on average, and over 2.2M in total. This characteristic makes the corpus a unique resource for the study of disagreements on anaphoric interpretation. A second distinctive feature is its rich annotation scheme, covering singletons, expletives, and split-antecedent plurals. Finally, the corpus also comes with labels inferred using a recently proposed probabilistic model of annotation for coreference. The labels are of high quality and make it possible to successfully train a state of the art coreference resolver, including training on singletons and non-referring expressions. The annotation model can also result in more than one label, or no label, being proposed for a markable, thus serving as a baseline method for automatically identifying ambiguous markables. A preliminary analysis of the results is presented.</abstract>
<identifier type="citekey">poesio-etal-2019-crowdsourced</identifier>
<identifier type="doi">10.18653/v1/N19-1176</identifier>
<location>
<url>https://aclanthology.org/N19-1176</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>1778</start>
<end>1789</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Crowdsourced Corpus of Multiple Judgments and Disagreement on Anaphoric Interpretation
%A Poesio, Massimo
%A Chamberlain, Jon
%A Paun, Silviu
%A Yu, Juntao
%A Uma, Alexandra
%A Kruschwitz, Udo
%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 poesio-etal-2019-crowdsourced
%X We present a corpus of anaphoric information (coreference) crowdsourced through a game-with-a-purpose. The corpus, containing annotations for about 108,000 markables, is one of the largest corpora for coreference for English, and one of the largest crowdsourced NLP corpora, but its main feature is the large number of judgments per markable: 20 on average, and over 2.2M in total. This characteristic makes the corpus a unique resource for the study of disagreements on anaphoric interpretation. A second distinctive feature is its rich annotation scheme, covering singletons, expletives, and split-antecedent plurals. Finally, the corpus also comes with labels inferred using a recently proposed probabilistic model of annotation for coreference. The labels are of high quality and make it possible to successfully train a state of the art coreference resolver, including training on singletons and non-referring expressions. The annotation model can also result in more than one label, or no label, being proposed for a markable, thus serving as a baseline method for automatically identifying ambiguous markables. A preliminary analysis of the results is presented.
%R 10.18653/v1/N19-1176
%U https://aclanthology.org/N19-1176
%U https://doi.org/10.18653/v1/N19-1176
%P 1778-1789
Markdown (Informal)
[A Crowdsourced Corpus of Multiple Judgments and Disagreement on Anaphoric Interpretation](https://aclanthology.org/N19-1176) (Poesio et al., NAACL 2019)
ACL
- Massimo Poesio, Jon Chamberlain, Silviu Paun, Juntao Yu, Alexandra Uma, and Udo Kruschwitz. 2019. A Crowdsourced Corpus of Multiple Judgments and Disagreement on Anaphoric Interpretation. In 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), pages 1778–1789, Minneapolis, Minnesota. Association for Computational Linguistics.