@inproceedings{drutsa-etal-2021-crowdsourcing,
title = "Crowdsourcing Natural Language Data at Scale: A Hands-On Tutorial",
author = "Drutsa, Alexey and
Ustalov, Dmitry and
Fedorova, Valentina and
Megorskaya, Olga and
Baidakova, Daria",
editor = "Kondrak, Greg and
Bontcheva, Kalina and
Gillick, Dan",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Tutorials",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-tutorials.6",
doi = "10.18653/v1/2021.naacl-tutorials.6",
pages = "25--30",
abstract = "In this tutorial, we present a portion of unique industry experience in efficient natural language data annotation via crowdsourcing shared by both leading researchers and engineers from Yandex. We will make an introduction to data labeling via public crowdsourcing marketplaces and will present the key components of efficient label collection. This will be followed by a practical session, where participants address a real-world language resource production task, experiment with selecting settings for the labeling process, and launch their label collection project on one of the largest crowdsourcing marketplaces. The projects will be run on real crowds within the tutorial session and we will present useful quality control techniques and provide the attendees with an opportunity to discuss their own annotation ideas.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="drutsa-etal-2021-crowdsourcing">
<titleInfo>
<title>Crowdsourcing Natural Language Data at Scale: A Hands-On Tutorial</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexey</namePart>
<namePart type="family">Drutsa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitry</namePart>
<namePart type="family">Ustalov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentina</namePart>
<namePart type="family">Fedorova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olga</namePart>
<namePart type="family">Megorskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daria</namePart>
<namePart type="family">Baidakova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Tutorials</title>
</titleInfo>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Kondrak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalina</namePart>
<namePart type="family">Bontcheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Gillick</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>In this tutorial, we present a portion of unique industry experience in efficient natural language data annotation via crowdsourcing shared by both leading researchers and engineers from Yandex. We will make an introduction to data labeling via public crowdsourcing marketplaces and will present the key components of efficient label collection. This will be followed by a practical session, where participants address a real-world language resource production task, experiment with selecting settings for the labeling process, and launch their label collection project on one of the largest crowdsourcing marketplaces. The projects will be run on real crowds within the tutorial session and we will present useful quality control techniques and provide the attendees with an opportunity to discuss their own annotation ideas.</abstract>
<identifier type="citekey">drutsa-etal-2021-crowdsourcing</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-tutorials.6</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-tutorials.6</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>25</start>
<end>30</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Crowdsourcing Natural Language Data at Scale: A Hands-On Tutorial
%A Drutsa, Alexey
%A Ustalov, Dmitry
%A Fedorova, Valentina
%A Megorskaya, Olga
%A Baidakova, Daria
%Y Kondrak, Greg
%Y Bontcheva, Kalina
%Y Gillick, Dan
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Tutorials
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F drutsa-etal-2021-crowdsourcing
%X In this tutorial, we present a portion of unique industry experience in efficient natural language data annotation via crowdsourcing shared by both leading researchers and engineers from Yandex. We will make an introduction to data labeling via public crowdsourcing marketplaces and will present the key components of efficient label collection. This will be followed by a practical session, where participants address a real-world language resource production task, experiment with selecting settings for the labeling process, and launch their label collection project on one of the largest crowdsourcing marketplaces. The projects will be run on real crowds within the tutorial session and we will present useful quality control techniques and provide the attendees with an opportunity to discuss their own annotation ideas.
%R 10.18653/v1/2021.naacl-tutorials.6
%U https://aclanthology.org/2021.naacl-tutorials.6
%U https://doi.org/10.18653/v1/2021.naacl-tutorials.6
%P 25-30
Markdown (Informal)
[Crowdsourcing Natural Language Data at Scale: A Hands-On Tutorial](https://aclanthology.org/2021.naacl-tutorials.6) (Drutsa et al., NAACL 2021)
ACL
- Alexey Drutsa, Dmitry Ustalov, Valentina Fedorova, Olga Megorskaya, and Daria Baidakova. 2021. Crowdsourcing Natural Language Data at Scale: A Hands-On Tutorial. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Tutorials, pages 25–30, Online. Association for Computational Linguistics.