@inproceedings{liang-etal-2024-optimizing,
title = "Optimizing Relation Extraction in Medical Texts through Active Learning: A Comparative Analysis of Trade-offs",
author = "Liang, Siting and
Valdunciel S{\'a}nchez, Pablo and
Sonntag, Daniel",
editor = {V{\'a}zquez, Ra{\'u}l and
Celikkanat, Hande and
Ulmer, Dennis and
Tiedemann, J{\"o}rg and
Swayamdipta, Swabha and
Aziz, Wilker and
Plank, Barbara and
Baan, Joris and
de Marneffe, Marie-Catherine},
booktitle = "Proceedings of the 1st Workshop on Uncertainty-Aware NLP (UncertaiNLP 2024)",
month = mar,
year = "2024",
address = "St Julians, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.uncertainlp-1.3",
pages = "23--34",
abstract = "This work explores the effectiveness of employing Clinical BERT for Relation Extraction (RE) tasks in medical texts within an Active Learning (AL) framework. Our main objective is to optimize RE in medical texts through AL while examining the trade-offs between performance and computation time, comparing it with alternative methods like Random Forest and BiLSTM networks. Comparisons extend to feature engineering requirements, performance metrics, and considerations of annotation costs, including AL step times and annotation rates. The utilization of AL strategies aligns with our broader goal of enhancing the efficiency of relation classification models, particularly when dealing with the challenges of annotating complex medical texts in a Human-in-the-Loop (HITL) setting. The results indicate that uncertainty-based sampling achieves comparable performance with significantly fewer annotated samples across three categories of supervised learning methods, thereby reducing annotation costs for clinical and biomedical corpora. While Clinical BERT exhibits clear performance advantages across two different corpora, the trade-off involves longer computation times in interactive annotation processes. In real-world applications, where practical feasibility and timely results are crucial, optimizing this trade-off becomes imperative.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liang-etal-2024-optimizing">
<titleInfo>
<title>Optimizing Relation Extraction in Medical Texts through Active Learning: A Comparative Analysis of Trade-offs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siting</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pablo</namePart>
<namePart type="family">Valdunciel Sánchez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Sonntag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Uncertainty-Aware NLP (UncertaiNLP 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="family">Vázquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hande</namePart>
<namePart type="family">Celikkanat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dennis</namePart>
<namePart type="family">Ulmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wilker</namePart>
<namePart type="family">Aziz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joris</namePart>
<namePart type="family">Baan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St Julians, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This work explores the effectiveness of employing Clinical BERT for Relation Extraction (RE) tasks in medical texts within an Active Learning (AL) framework. Our main objective is to optimize RE in medical texts through AL while examining the trade-offs between performance and computation time, comparing it with alternative methods like Random Forest and BiLSTM networks. Comparisons extend to feature engineering requirements, performance metrics, and considerations of annotation costs, including AL step times and annotation rates. The utilization of AL strategies aligns with our broader goal of enhancing the efficiency of relation classification models, particularly when dealing with the challenges of annotating complex medical texts in a Human-in-the-Loop (HITL) setting. The results indicate that uncertainty-based sampling achieves comparable performance with significantly fewer annotated samples across three categories of supervised learning methods, thereby reducing annotation costs for clinical and biomedical corpora. While Clinical BERT exhibits clear performance advantages across two different corpora, the trade-off involves longer computation times in interactive annotation processes. In real-world applications, where practical feasibility and timely results are crucial, optimizing this trade-off becomes imperative.</abstract>
<identifier type="citekey">liang-etal-2024-optimizing</identifier>
<location>
<url>https://aclanthology.org/2024.uncertainlp-1.3</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>23</start>
<end>34</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Optimizing Relation Extraction in Medical Texts through Active Learning: A Comparative Analysis of Trade-offs
%A Liang, Siting
%A Valdunciel Sánchez, Pablo
%A Sonntag, Daniel
%Y Vázquez, Raúl
%Y Celikkanat, Hande
%Y Ulmer, Dennis
%Y Tiedemann, Jörg
%Y Swayamdipta, Swabha
%Y Aziz, Wilker
%Y Plank, Barbara
%Y Baan, Joris
%Y de Marneffe, Marie-Catherine
%S Proceedings of the 1st Workshop on Uncertainty-Aware NLP (UncertaiNLP 2024)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St Julians, Malta
%F liang-etal-2024-optimizing
%X This work explores the effectiveness of employing Clinical BERT for Relation Extraction (RE) tasks in medical texts within an Active Learning (AL) framework. Our main objective is to optimize RE in medical texts through AL while examining the trade-offs between performance and computation time, comparing it with alternative methods like Random Forest and BiLSTM networks. Comparisons extend to feature engineering requirements, performance metrics, and considerations of annotation costs, including AL step times and annotation rates. The utilization of AL strategies aligns with our broader goal of enhancing the efficiency of relation classification models, particularly when dealing with the challenges of annotating complex medical texts in a Human-in-the-Loop (HITL) setting. The results indicate that uncertainty-based sampling achieves comparable performance with significantly fewer annotated samples across three categories of supervised learning methods, thereby reducing annotation costs for clinical and biomedical corpora. While Clinical BERT exhibits clear performance advantages across two different corpora, the trade-off involves longer computation times in interactive annotation processes. In real-world applications, where practical feasibility and timely results are crucial, optimizing this trade-off becomes imperative.
%U https://aclanthology.org/2024.uncertainlp-1.3
%P 23-34
Markdown (Informal)
[Optimizing Relation Extraction in Medical Texts through Active Learning: A Comparative Analysis of Trade-offs](https://aclanthology.org/2024.uncertainlp-1.3) (Liang et al., UncertaiNLP-WS 2024)
ACL