@inproceedings{chamberlain-etal-2016-phrase,
title = "Phrase Detectives Corpus 1.0 Crowdsourced Anaphoric Coreference.",
author = "Chamberlain, Jon and
Poesio, Massimo and
Kruschwitz, Udo",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1323",
pages = "2039--2046",
abstract = "Natural Language Engineering tasks require large and complex annotated datasets to build more advanced models of language. Corpora are typically annotated by several experts to create a gold standard; however, there are now compelling reasons to use a non-expert crowd to annotate text, driven by cost, speed and scalability. Phrase Detectives Corpus 1.0 is an anaphorically-annotated corpus of encyclopedic and narrative text that contains a gold standard created by multiple experts, as well as a set of annotations created by a large non-expert crowd. Analysis shows very good inter-expert agreement (kappa=.88-.93) but a more variable baseline crowd agreement (kappa=.52-.96). Encyclopedic texts show less agreement (and by implication are harder to annotate) than narrative texts. The release of this corpus is intended to encourage research into the use of crowds for text annotation and the development of more advanced, probabilistic language models, in particular for anaphoric coreference.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chamberlain-etal-2016-phrase">
<titleInfo>
<title>Phrase Detectives Corpus 1.0 Crowdsourced Anaphoric Coreference.</title>
</titleInfo>
<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">Massimo</namePart>
<namePart type="family">Poesio</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>2016-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Natural Language Engineering tasks require large and complex annotated datasets to build more advanced models of language. Corpora are typically annotated by several experts to create a gold standard; however, there are now compelling reasons to use a non-expert crowd to annotate text, driven by cost, speed and scalability. Phrase Detectives Corpus 1.0 is an anaphorically-annotated corpus of encyclopedic and narrative text that contains a gold standard created by multiple experts, as well as a set of annotations created by a large non-expert crowd. Analysis shows very good inter-expert agreement (kappa=.88-.93) but a more variable baseline crowd agreement (kappa=.52-.96). Encyclopedic texts show less agreement (and by implication are harder to annotate) than narrative texts. The release of this corpus is intended to encourage research into the use of crowds for text annotation and the development of more advanced, probabilistic language models, in particular for anaphoric coreference.</abstract>
<identifier type="citekey">chamberlain-etal-2016-phrase</identifier>
<location>
<url>https://aclanthology.org/L16-1323</url>
</location>
<part>
<date>2016-may</date>
<extent unit="page">
<start>2039</start>
<end>2046</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Phrase Detectives Corpus 1.0 Crowdsourced Anaphoric Coreference.
%A Chamberlain, Jon
%A Poesio, Massimo
%A Kruschwitz, Udo
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 may
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F chamberlain-etal-2016-phrase
%X Natural Language Engineering tasks require large and complex annotated datasets to build more advanced models of language. Corpora are typically annotated by several experts to create a gold standard; however, there are now compelling reasons to use a non-expert crowd to annotate text, driven by cost, speed and scalability. Phrase Detectives Corpus 1.0 is an anaphorically-annotated corpus of encyclopedic and narrative text that contains a gold standard created by multiple experts, as well as a set of annotations created by a large non-expert crowd. Analysis shows very good inter-expert agreement (kappa=.88-.93) but a more variable baseline crowd agreement (kappa=.52-.96). Encyclopedic texts show less agreement (and by implication are harder to annotate) than narrative texts. The release of this corpus is intended to encourage research into the use of crowds for text annotation and the development of more advanced, probabilistic language models, in particular for anaphoric coreference.
%U https://aclanthology.org/L16-1323
%P 2039-2046
Markdown (Informal)
[Phrase Detectives Corpus 1.0 Crowdsourced Anaphoric Coreference.](https://aclanthology.org/L16-1323) (Chamberlain et al., LREC 2016)
ACL