@inproceedings{ning-etal-2020-easy,
title = "Easy, Reproducible and Quality-Controlled Data Collection with {CROWDAQ}",
author = "Ning, Qiang and
Wu, Hao and
Dasigi, Pradeep and
Dua, Dheeru and
Gardner, Matt and
Logan IV, Robert L. and
Marasovi{\'c}, Ana and
Nie, Zhen",
editor = "Liu, Qun and
Schlangen, David",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = oct,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-demos.17",
doi = "10.18653/v1/2020.emnlp-demos.17",
pages = "127--134",
abstract = "High-quality and large-scale data are key to success for AI systems. However, large-scale data annotation efforts are often confronted with a set of common challenges: (1) designing a user-friendly annotation interface; (2) training enough annotators efficiently; and (3) reproducibility. To address these problems, we introduce CROWDAQ, an open-source platform that standardizes the data collection pipeline with customizable user-interface components, automated annotator qualification, and saved pipelines in a re-usable format. We show that CROWDAQ simplifies data annotation significantly on a diverse set of data collection use cases and we hope it will be a convenient tool for the community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ning-etal-2020-easy">
<titleInfo>
<title>Easy, Reproducible and Quality-Controlled Data Collection with CROWDAQ</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qiang</namePart>
<namePart type="family">Ning</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pradeep</namePart>
<namePart type="family">Dasigi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dheeru</namePart>
<namePart type="family">Dua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Gardner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Logan IV</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="family">Marasović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Nie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Schlangen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>High-quality and large-scale data are key to success for AI systems. However, large-scale data annotation efforts are often confronted with a set of common challenges: (1) designing a user-friendly annotation interface; (2) training enough annotators efficiently; and (3) reproducibility. To address these problems, we introduce CROWDAQ, an open-source platform that standardizes the data collection pipeline with customizable user-interface components, automated annotator qualification, and saved pipelines in a re-usable format. We show that CROWDAQ simplifies data annotation significantly on a diverse set of data collection use cases and we hope it will be a convenient tool for the community.</abstract>
<identifier type="citekey">ning-etal-2020-easy</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-demos.17</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-demos.17</url>
</location>
<part>
<date>2020-10</date>
<extent unit="page">
<start>127</start>
<end>134</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Easy, Reproducible and Quality-Controlled Data Collection with CROWDAQ
%A Ning, Qiang
%A Wu, Hao
%A Dasigi, Pradeep
%A Dua, Dheeru
%A Gardner, Matt
%A Logan IV, Robert L.
%A Marasović, Ana
%A Nie, Zhen
%Y Liu, Qun
%Y Schlangen, David
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2020
%8 October
%I Association for Computational Linguistics
%C Online
%F ning-etal-2020-easy
%X High-quality and large-scale data are key to success for AI systems. However, large-scale data annotation efforts are often confronted with a set of common challenges: (1) designing a user-friendly annotation interface; (2) training enough annotators efficiently; and (3) reproducibility. To address these problems, we introduce CROWDAQ, an open-source platform that standardizes the data collection pipeline with customizable user-interface components, automated annotator qualification, and saved pipelines in a re-usable format. We show that CROWDAQ simplifies data annotation significantly on a diverse set of data collection use cases and we hope it will be a convenient tool for the community.
%R 10.18653/v1/2020.emnlp-demos.17
%U https://aclanthology.org/2020.emnlp-demos.17
%U https://doi.org/10.18653/v1/2020.emnlp-demos.17
%P 127-134
Markdown (Informal)
[Easy, Reproducible and Quality-Controlled Data Collection with CROWDAQ](https://aclanthology.org/2020.emnlp-demos.17) (Ning et al., EMNLP 2020)
ACL
- Qiang Ning, Hao Wu, Pradeep Dasigi, Dheeru Dua, Matt Gardner, Robert L. Logan IV, Ana Marasović, and Zhen Nie. 2020. Easy, Reproducible and Quality-Controlled Data Collection with CROWDAQ. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 127–134, Online. Association for Computational Linguistics.