@inproceedings{parde-nielsen-2017-finding,
title = "Finding Patterns in Noisy Crowds: Regression-based Annotation Aggregation for Crowdsourced Data",
author = "Parde, Natalie and
Nielsen, Rodney",
editor = "Palmer, Martha and
Hwa, Rebecca and
Riedel, Sebastian",
booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
month = sep,
year = "2017",
address = "Copenhagen, Denmark",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D17-1204",
doi = "10.18653/v1/D17-1204",
pages = "1907--1912",
abstract = "Crowdsourcing offers a convenient means of obtaining labeled data quickly and inexpensively. However, crowdsourced labels are often noisier than expert-annotated data, making it difficult to aggregate them meaningfully. We present an aggregation approach that learns a regression model from crowdsourced annotations to predict aggregated labels for instances that have no expert adjudications. The predicted labels achieve a correlation of 0.594 with expert labels on our data, outperforming the best alternative aggregation method by 11.9{\%}. Our approach also outperforms the alternatives on third-party datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="parde-nielsen-2017-finding">
<titleInfo>
<title>Finding Patterns in Noisy Crowds: Regression-based Annotation Aggregation for Crowdsourced Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Parde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodney</namePart>
<namePart type="family">Nielsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martha</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Hwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Riedel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Copenhagen, Denmark</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Crowdsourcing offers a convenient means of obtaining labeled data quickly and inexpensively. However, crowdsourced labels are often noisier than expert-annotated data, making it difficult to aggregate them meaningfully. We present an aggregation approach that learns a regression model from crowdsourced annotations to predict aggregated labels for instances that have no expert adjudications. The predicted labels achieve a correlation of 0.594 with expert labels on our data, outperforming the best alternative aggregation method by 11.9%. Our approach also outperforms the alternatives on third-party datasets.</abstract>
<identifier type="citekey">parde-nielsen-2017-finding</identifier>
<identifier type="doi">10.18653/v1/D17-1204</identifier>
<location>
<url>https://aclanthology.org/D17-1204</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>1907</start>
<end>1912</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Finding Patterns in Noisy Crowds: Regression-based Annotation Aggregation for Crowdsourced Data
%A Parde, Natalie
%A Nielsen, Rodney
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F parde-nielsen-2017-finding
%X Crowdsourcing offers a convenient means of obtaining labeled data quickly and inexpensively. However, crowdsourced labels are often noisier than expert-annotated data, making it difficult to aggregate them meaningfully. We present an aggregation approach that learns a regression model from crowdsourced annotations to predict aggregated labels for instances that have no expert adjudications. The predicted labels achieve a correlation of 0.594 with expert labels on our data, outperforming the best alternative aggregation method by 11.9%. Our approach also outperforms the alternatives on third-party datasets.
%R 10.18653/v1/D17-1204
%U https://aclanthology.org/D17-1204
%U https://doi.org/10.18653/v1/D17-1204
%P 1907-1912
Markdown (Informal)
[Finding Patterns in Noisy Crowds: Regression-based Annotation Aggregation for Crowdsourced Data](https://aclanthology.org/D17-1204) (Parde & Nielsen, EMNLP 2017)
ACL