@inproceedings{scholman-etal-2022-design,
title = "Design Choices in Crowdsourcing Discourse Relation Annotations: The Effect of Worker Selection and Training",
author = "Scholman, Merel and
Pyatkin, Valentina and
Yung, Frances and
Dagan, Ido and
Tsarfaty, Reut and
Demberg, Vera",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.231",
pages = "2148--2156",
abstract = "Obtaining linguistic annotation from novice crowdworkers is far from trivial. A case in point is the annotation of discourse relations, which is a complicated task. Recent methods have obtained promising results by extracting relation labels from either discourse connectives (DCs) or question-answer (QA) pairs that participants provide. The current contribution studies the effect of worker selection and training on the agreement on implicit relation labels between workers and gold labels, for both the DC and the QA method. In Study 1, workers were not specifically selected or trained, and the results show that there is much room for improvement. Study 2 shows that a combination of selection and training does lead to improved results, but the method is cost- and time-intensive. Study 3 shows that a selection-only approach is a viable alternative; it results in annotations of comparable quality compared to annotations from trained participants. The results generalized over both the DC and QA method and therefore indicate that a selection-only approach could also be effective for other crowdsourced discourse annotation tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scholman-etal-2022-design">
<titleInfo>
<title>Design Choices in Crowdsourcing Discourse Relation Annotations: The Effect of Worker Selection and Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Merel</namePart>
<namePart type="family">Scholman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentina</namePart>
<namePart type="family">Pyatkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frances</namePart>
<namePart type="family">Yung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ido</namePart>
<namePart type="family">Dagan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Obtaining linguistic annotation from novice crowdworkers is far from trivial. A case in point is the annotation of discourse relations, which is a complicated task. Recent methods have obtained promising results by extracting relation labels from either discourse connectives (DCs) or question-answer (QA) pairs that participants provide. The current contribution studies the effect of worker selection and training on the agreement on implicit relation labels between workers and gold labels, for both the DC and the QA method. In Study 1, workers were not specifically selected or trained, and the results show that there is much room for improvement. Study 2 shows that a combination of selection and training does lead to improved results, but the method is cost- and time-intensive. Study 3 shows that a selection-only approach is a viable alternative; it results in annotations of comparable quality compared to annotations from trained participants. The results generalized over both the DC and QA method and therefore indicate that a selection-only approach could also be effective for other crowdsourced discourse annotation tasks.</abstract>
<identifier type="citekey">scholman-etal-2022-design</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.231</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>2148</start>
<end>2156</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Design Choices in Crowdsourcing Discourse Relation Annotations: The Effect of Worker Selection and Training
%A Scholman, Merel
%A Pyatkin, Valentina
%A Yung, Frances
%A Dagan, Ido
%A Tsarfaty, Reut
%A Demberg, Vera
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F scholman-etal-2022-design
%X Obtaining linguistic annotation from novice crowdworkers is far from trivial. A case in point is the annotation of discourse relations, which is a complicated task. Recent methods have obtained promising results by extracting relation labels from either discourse connectives (DCs) or question-answer (QA) pairs that participants provide. The current contribution studies the effect of worker selection and training on the agreement on implicit relation labels between workers and gold labels, for both the DC and the QA method. In Study 1, workers were not specifically selected or trained, and the results show that there is much room for improvement. Study 2 shows that a combination of selection and training does lead to improved results, but the method is cost- and time-intensive. Study 3 shows that a selection-only approach is a viable alternative; it results in annotations of comparable quality compared to annotations from trained participants. The results generalized over both the DC and QA method and therefore indicate that a selection-only approach could also be effective for other crowdsourced discourse annotation tasks.
%U https://aclanthology.org/2022.lrec-1.231
%P 2148-2156
Markdown (Informal)
[Design Choices in Crowdsourcing Discourse Relation Annotations: The Effect of Worker Selection and Training](https://aclanthology.org/2022.lrec-1.231) (Scholman et al., LREC 2022)
ACL