@inproceedings{li-etal-2020-neural,
title = "A Neural Model for Aggregating Coreference Annotation in Crowdsourcing",
author = "Li, Maolin and
Takamura, Hiroya and
Ananiadou, Sophia",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.507/",
doi = "10.18653/v1/2020.coling-main.507",
pages = "5760--5773",
abstract = "Coreference resolution is the task of identifying all mentions in a text that refer to the same real-world entity. Collecting sufficient labelled data from expert annotators to train a high-performance coreference resolution system is time-consuming and expensive. Crowdsourcing makes it possible to obtain the required amounts of data rapidly and cost-effectively. However, crowd-sourced labels can be noisy. To ensure high-quality data, it is crucial to infer the correct labels by aggregating the noisy labels. In this paper, we split the aggregation into two subtasks, i.e, mention classification and coreference chain inference. Firstly, we predict the general class of each mention using an autoencoder, which incorporates contextual information about each mention, while at the same time taking into account the mention`s annotation complexity and annotators' reliability at different levels. Secondly, to determine the coreference chain of each mention, we use weighted voting which takes into account the learned reliability in the first subtask. Experimental results demonstrate the effectiveness of our method in predicting the correct labels. We also illustrate our model`s interpretability through a comprehensive analysis of experimental results."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2020-neural">
<titleInfo>
<title>A Neural Model for Aggregating Coreference Annotation in Crowdsourcing</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">Hiroya</namePart>
<namePart type="family">Takamura</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>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Coreference resolution is the task of identifying all mentions in a text that refer to the same real-world entity. Collecting sufficient labelled data from expert annotators to train a high-performance coreference resolution system is time-consuming and expensive. Crowdsourcing makes it possible to obtain the required amounts of data rapidly and cost-effectively. However, crowd-sourced labels can be noisy. To ensure high-quality data, it is crucial to infer the correct labels by aggregating the noisy labels. In this paper, we split the aggregation into two subtasks, i.e, mention classification and coreference chain inference. Firstly, we predict the general class of each mention using an autoencoder, which incorporates contextual information about each mention, while at the same time taking into account the mention‘s annotation complexity and annotators’ reliability at different levels. Secondly, to determine the coreference chain of each mention, we use weighted voting which takes into account the learned reliability in the first subtask. Experimental results demonstrate the effectiveness of our method in predicting the correct labels. We also illustrate our model‘s interpretability through a comprehensive analysis of experimental results.</abstract>
<identifier type="citekey">li-etal-2020-neural</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.507</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.507/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>5760</start>
<end>5773</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Neural Model for Aggregating Coreference Annotation in Crowdsourcing
%A Li, Maolin
%A Takamura, Hiroya
%A Ananiadou, Sophia
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F li-etal-2020-neural
%X Coreference resolution is the task of identifying all mentions in a text that refer to the same real-world entity. Collecting sufficient labelled data from expert annotators to train a high-performance coreference resolution system is time-consuming and expensive. Crowdsourcing makes it possible to obtain the required amounts of data rapidly and cost-effectively. However, crowd-sourced labels can be noisy. To ensure high-quality data, it is crucial to infer the correct labels by aggregating the noisy labels. In this paper, we split the aggregation into two subtasks, i.e, mention classification and coreference chain inference. Firstly, we predict the general class of each mention using an autoencoder, which incorporates contextual information about each mention, while at the same time taking into account the mention‘s annotation complexity and annotators’ reliability at different levels. Secondly, to determine the coreference chain of each mention, we use weighted voting which takes into account the learned reliability in the first subtask. Experimental results demonstrate the effectiveness of our method in predicting the correct labels. We also illustrate our model‘s interpretability through a comprehensive analysis of experimental results.
%R 10.18653/v1/2020.coling-main.507
%U https://aclanthology.org/2020.coling-main.507/
%U https://doi.org/10.18653/v1/2020.coling-main.507
%P 5760-5773
Markdown (Informal)
[A Neural Model for Aggregating Coreference Annotation in Crowdsourcing](https://aclanthology.org/2020.coling-main.507/) (Li et al., COLING 2020)
ACL