@inproceedings{li-etal-2019-modelling,
title = "Modelling Instance-Level Annotator Reliability for Natural Language Labelling Tasks",
author = {Li, Maolin and
Fahlstr{\"o}m Myrman, Arvid and
Mu, Tingting and
Ananiadou, Sophia},
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1295",
doi = "10.18653/v1/N19-1295",
pages = "2873--2883",
abstract = "When constructing models that learn from noisy labels produced by multiple annotators, it is important to accurately estimate the reliability of annotators. Annotators may provide labels of inconsistent quality due to their varying expertise and reliability in a domain. Previous studies have mostly focused on estimating each annotator{'}s overall reliability on the entire annotation task. However, in practice, the reliability of an annotator may depend on each specific instance. Only a limited number of studies have investigated modelling per-instance reliability and these only considered binary labels. In this paper, we propose an unsupervised model which can handle both binary and multi-class labels. It can automatically estimate the per-instance reliability of each annotator and the correct label for each instance. We specify our model as a probabilistic model which incorporates neural networks to model the dependency between latent variables and instances. For evaluation, the proposed method is applied to both synthetic and real data, including two labelling tasks: text classification and textual entailment. Experimental results demonstrate our novel method can not only accurately estimate the reliability of annotators across different instances, but also achieve superior performance in predicting the correct labels and detecting the least reliable annotators compared to state-of-the-art baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2019-modelling">
<titleInfo>
<title>Modelling Instance-Level Annotator Reliability for Natural Language Labelling Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maolin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arvid</namePart>
<namePart type="family">Fahlström Myrman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tingting</namePart>
<namePart type="family">Mu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>When constructing models that learn from noisy labels produced by multiple annotators, it is important to accurately estimate the reliability of annotators. Annotators may provide labels of inconsistent quality due to their varying expertise and reliability in a domain. Previous studies have mostly focused on estimating each annotator’s overall reliability on the entire annotation task. However, in practice, the reliability of an annotator may depend on each specific instance. Only a limited number of studies have investigated modelling per-instance reliability and these only considered binary labels. In this paper, we propose an unsupervised model which can handle both binary and multi-class labels. It can automatically estimate the per-instance reliability of each annotator and the correct label for each instance. We specify our model as a probabilistic model which incorporates neural networks to model the dependency between latent variables and instances. For evaluation, the proposed method is applied to both synthetic and real data, including two labelling tasks: text classification and textual entailment. Experimental results demonstrate our novel method can not only accurately estimate the reliability of annotators across different instances, but also achieve superior performance in predicting the correct labels and detecting the least reliable annotators compared to state-of-the-art baselines.</abstract>
<identifier type="citekey">li-etal-2019-modelling</identifier>
<identifier type="doi">10.18653/v1/N19-1295</identifier>
<location>
<url>https://aclanthology.org/N19-1295</url>
</location>
<part>
<date>2019-jun</date>
<extent unit="page">
<start>2873</start>
<end>2883</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modelling Instance-Level Annotator Reliability for Natural Language Labelling Tasks
%A Li, Maolin
%A Fahlström Myrman, Arvid
%A Mu, Tingting
%A Ananiadou, Sophia
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 jun
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F li-etal-2019-modelling
%X When constructing models that learn from noisy labels produced by multiple annotators, it is important to accurately estimate the reliability of annotators. Annotators may provide labels of inconsistent quality due to their varying expertise and reliability in a domain. Previous studies have mostly focused on estimating each annotator’s overall reliability on the entire annotation task. However, in practice, the reliability of an annotator may depend on each specific instance. Only a limited number of studies have investigated modelling per-instance reliability and these only considered binary labels. In this paper, we propose an unsupervised model which can handle both binary and multi-class labels. It can automatically estimate the per-instance reliability of each annotator and the correct label for each instance. We specify our model as a probabilistic model which incorporates neural networks to model the dependency between latent variables and instances. For evaluation, the proposed method is applied to both synthetic and real data, including two labelling tasks: text classification and textual entailment. Experimental results demonstrate our novel method can not only accurately estimate the reliability of annotators across different instances, but also achieve superior performance in predicting the correct labels and detecting the least reliable annotators compared to state-of-the-art baselines.
%R 10.18653/v1/N19-1295
%U https://aclanthology.org/N19-1295
%U https://doi.org/10.18653/v1/N19-1295
%P 2873-2883
Markdown (Informal)
[Modelling Instance-Level Annotator Reliability for Natural Language Labelling Tasks](https://aclanthology.org/N19-1295) (Li et al., NAACL 2019)
ACL
- Maolin Li, Arvid Fahlström Myrman, Tingting Mu, and Sophia Ananiadou. 2019. Modelling Instance-Level Annotator Reliability for Natural Language Labelling Tasks. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2873–2883, Minneapolis, Minnesota. Association for Computational Linguistics.