@inproceedings{mathur-etal-2017-sequence,
title = "Sequence Effects in Crowdsourced Annotations",
author = "Mathur, Nitika and
Baldwin, Timothy and
Cohn, Trevor",
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/D17-1306",
doi = "10.18653/v1/D17-1306",
pages = "2860--2865",
abstract = "Manual data annotation is a vital component of NLP research. When designing annotation tasks, properties of the annotation interface can unintentionally lead to artefacts in the resulting dataset, biasing the evaluation. In this paper, we explore sequence effects where annotations of an item are affected by the preceding items. Having assigned one label to an instance, the annotator may be less (or more) likely to assign the same label to the next. During rating tasks, seeing a low quality item may affect the score given to the next item either positively or negatively. We see clear evidence of both types of effects using auto-correlation studies over three different crowdsourced datasets. We then recommend a simple way to minimise sequence effects.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mathur-etal-2017-sequence">
<titleInfo>
<title>Sequence Effects in Crowdsourced Annotations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nitika</namePart>
<namePart type="family">Mathur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</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>Manual data annotation is a vital component of NLP research. When designing annotation tasks, properties of the annotation interface can unintentionally lead to artefacts in the resulting dataset, biasing the evaluation. In this paper, we explore sequence effects where annotations of an item are affected by the preceding items. Having assigned one label to an instance, the annotator may be less (or more) likely to assign the same label to the next. During rating tasks, seeing a low quality item may affect the score given to the next item either positively or negatively. We see clear evidence of both types of effects using auto-correlation studies over three different crowdsourced datasets. We then recommend a simple way to minimise sequence effects.</abstract>
<identifier type="citekey">mathur-etal-2017-sequence</identifier>
<identifier type="doi">10.18653/v1/D17-1306</identifier>
<location>
<url>https://aclanthology.org/D17-1306</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>2860</start>
<end>2865</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sequence Effects in Crowdsourced Annotations
%A Mathur, Nitika
%A Baldwin, Timothy
%A Cohn, Trevor
%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 mathur-etal-2017-sequence
%X Manual data annotation is a vital component of NLP research. When designing annotation tasks, properties of the annotation interface can unintentionally lead to artefacts in the resulting dataset, biasing the evaluation. In this paper, we explore sequence effects where annotations of an item are affected by the preceding items. Having assigned one label to an instance, the annotator may be less (or more) likely to assign the same label to the next. During rating tasks, seeing a low quality item may affect the score given to the next item either positively or negatively. We see clear evidence of both types of effects using auto-correlation studies over three different crowdsourced datasets. We then recommend a simple way to minimise sequence effects.
%R 10.18653/v1/D17-1306
%U https://aclanthology.org/D17-1306
%U https://doi.org/10.18653/v1/D17-1306
%P 2860-2865
Markdown (Informal)
[Sequence Effects in Crowdsourced Annotations](https://aclanthology.org/D17-1306) (Mathur et al., EMNLP 2017)
ACL
- Nitika Mathur, Timothy Baldwin, and Trevor Cohn. 2017. Sequence Effects in Crowdsourced Annotations. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2860–2865, Copenhagen, Denmark. Association for Computational Linguistics.