@inproceedings{zlabinger-etal-2020-effective,
title = "Effective Crowd-Annotation of Participants, Interventions, and Outcomes in the Text of Clinical Trial Reports",
author = {Zlabinger, Markus and
Sabou, Marta and
Hofst{\"a}tter, Sebastian and
Hanbury, Allan},
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.274",
doi = "10.18653/v1/2020.findings-emnlp.274",
pages = "3064--3074",
abstract = "The search for Participants, Interventions, and Outcomes (PIO) in clinical trial reports is a critical task in Evidence Based Medicine. For an automatic PIO extraction, high-quality corpora are needed. Obtaining such a corpus from crowdworkers, however, has been shown to be ineffective since (i) workers usually lack domain-specific expertise to conduct the task with sufficient quality, and (ii) the standard approach of annotating entire abstracts of trial reports as one task-instance (i.e. HIT) leads to an uneven distribution in task effort. In this paper, we switch from entire abstract to sentence annotation, referred to as the SenBase approach. We build upon SenBase in SenSupport, where we compensate the lack of domain-specific expertise of crowdworkers by showing for each task-instance similar sentences that are already annotated by experts. Such tailored task-instance examples are retrieved via unsupervised semantic short-text similarity (SSTS) method {--} and we evaluate nine methods to find an effective solution for SenSupport. We compute the Cohen{'}s Kappa agreement between crowd-annotations and gold standard annotations and show that (i) both sentence-based approaches outperform a Baseline approach where entire abstracts are annotated; (ii) supporting annotators with tailored task-instance examples is the best performing approach with Kappa agreements of 0.78/0.75/0.69 for P, I, and O respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zlabinger-etal-2020-effective">
<titleInfo>
<title>Effective Crowd-Annotation of Participants, Interventions, and Outcomes in the Text of Clinical Trial Reports</title>
</titleInfo>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Zlabinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="family">Sabou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Hofstätter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Allan</namePart>
<namePart type="family">Hanbury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>The search for Participants, Interventions, and Outcomes (PIO) in clinical trial reports is a critical task in Evidence Based Medicine. For an automatic PIO extraction, high-quality corpora are needed. Obtaining such a corpus from crowdworkers, however, has been shown to be ineffective since (i) workers usually lack domain-specific expertise to conduct the task with sufficient quality, and (ii) the standard approach of annotating entire abstracts of trial reports as one task-instance (i.e. HIT) leads to an uneven distribution in task effort. In this paper, we switch from entire abstract to sentence annotation, referred to as the SenBase approach. We build upon SenBase in SenSupport, where we compensate the lack of domain-specific expertise of crowdworkers by showing for each task-instance similar sentences that are already annotated by experts. Such tailored task-instance examples are retrieved via unsupervised semantic short-text similarity (SSTS) method – and we evaluate nine methods to find an effective solution for SenSupport. We compute the Cohen’s Kappa agreement between crowd-annotations and gold standard annotations and show that (i) both sentence-based approaches outperform a Baseline approach where entire abstracts are annotated; (ii) supporting annotators with tailored task-instance examples is the best performing approach with Kappa agreements of 0.78/0.75/0.69 for P, I, and O respectively.</abstract>
<identifier type="citekey">zlabinger-etal-2020-effective</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.274</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.274</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3064</start>
<end>3074</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Effective Crowd-Annotation of Participants, Interventions, and Outcomes in the Text of Clinical Trial Reports
%A Zlabinger, Markus
%A Sabou, Marta
%A Hofstätter, Sebastian
%A Hanbury, Allan
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F zlabinger-etal-2020-effective
%X The search for Participants, Interventions, and Outcomes (PIO) in clinical trial reports is a critical task in Evidence Based Medicine. For an automatic PIO extraction, high-quality corpora are needed. Obtaining such a corpus from crowdworkers, however, has been shown to be ineffective since (i) workers usually lack domain-specific expertise to conduct the task with sufficient quality, and (ii) the standard approach of annotating entire abstracts of trial reports as one task-instance (i.e. HIT) leads to an uneven distribution in task effort. In this paper, we switch from entire abstract to sentence annotation, referred to as the SenBase approach. We build upon SenBase in SenSupport, where we compensate the lack of domain-specific expertise of crowdworkers by showing for each task-instance similar sentences that are already annotated by experts. Such tailored task-instance examples are retrieved via unsupervised semantic short-text similarity (SSTS) method – and we evaluate nine methods to find an effective solution for SenSupport. We compute the Cohen’s Kappa agreement between crowd-annotations and gold standard annotations and show that (i) both sentence-based approaches outperform a Baseline approach where entire abstracts are annotated; (ii) supporting annotators with tailored task-instance examples is the best performing approach with Kappa agreements of 0.78/0.75/0.69 for P, I, and O respectively.
%R 10.18653/v1/2020.findings-emnlp.274
%U https://aclanthology.org/2020.findings-emnlp.274
%U https://doi.org/10.18653/v1/2020.findings-emnlp.274
%P 3064-3074
Markdown (Informal)
[Effective Crowd-Annotation of Participants, Interventions, and Outcomes in the Text of Clinical Trial Reports](https://aclanthology.org/2020.findings-emnlp.274) (Zlabinger et al., Findings 2020)
ACL