@inproceedings{kim-nakashole-2022-data,
title = "Data Augmentation for Rare Symptoms in Vaccine Side-Effect Detection",
author = "Kim, Bosung and
Nakashole, Ndapa",
editor = "Demner-Fushman, Dina and
Cohen, Kevin Bretonnel and
Ananiadou, Sophia and
Tsujii, Junichi",
booktitle = "Proceedings of the 21st Workshop on Biomedical Language Processing",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.bionlp-1.29",
doi = "10.18653/v1/2022.bionlp-1.29",
pages = "310--315",
abstract = "We study the problem of entity detection and normalization applied to patient self-reports of symptoms that arise as side-effects of vaccines. Our application domain presents unique challenges that render traditional classification methods ineffective: the number of entity types is large; and many symptoms are rare, resulting in a long-tail distribution of training examples per entity type. We tackle these challenges with an autoregressive model that generates standardized names of symptoms. We introduce a data augmentation technique to increase the number of training examples for rare symptoms. Experiments on real-life patient vaccine symptom self-reports show that our approach outperforms strong baselines, and that additional examples improve performance on the long-tail entities.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-nakashole-2022-data">
<titleInfo>
<title>Data Augmentation for Rare Symptoms in Vaccine Side-Effect Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bosung</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ndapa</namePart>
<namePart type="family">Nakashole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st Workshop on Biomedical Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="given">Bretonnel</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We study the problem of entity detection and normalization applied to patient self-reports of symptoms that arise as side-effects of vaccines. Our application domain presents unique challenges that render traditional classification methods ineffective: the number of entity types is large; and many symptoms are rare, resulting in a long-tail distribution of training examples per entity type. We tackle these challenges with an autoregressive model that generates standardized names of symptoms. We introduce a data augmentation technique to increase the number of training examples for rare symptoms. Experiments on real-life patient vaccine symptom self-reports show that our approach outperforms strong baselines, and that additional examples improve performance on the long-tail entities.</abstract>
<identifier type="citekey">kim-nakashole-2022-data</identifier>
<identifier type="doi">10.18653/v1/2022.bionlp-1.29</identifier>
<location>
<url>https://aclanthology.org/2022.bionlp-1.29</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>310</start>
<end>315</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Augmentation for Rare Symptoms in Vaccine Side-Effect Detection
%A Kim, Bosung
%A Nakashole, Ndapa
%Y Demner-Fushman, Dina
%Y Cohen, Kevin Bretonnel
%Y Ananiadou, Sophia
%Y Tsujii, Junichi
%S Proceedings of the 21st Workshop on Biomedical Language Processing
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F kim-nakashole-2022-data
%X We study the problem of entity detection and normalization applied to patient self-reports of symptoms that arise as side-effects of vaccines. Our application domain presents unique challenges that render traditional classification methods ineffective: the number of entity types is large; and many symptoms are rare, resulting in a long-tail distribution of training examples per entity type. We tackle these challenges with an autoregressive model that generates standardized names of symptoms. We introduce a data augmentation technique to increase the number of training examples for rare symptoms. Experiments on real-life patient vaccine symptom self-reports show that our approach outperforms strong baselines, and that additional examples improve performance on the long-tail entities.
%R 10.18653/v1/2022.bionlp-1.29
%U https://aclanthology.org/2022.bionlp-1.29
%U https://doi.org/10.18653/v1/2022.bionlp-1.29
%P 310-315
Markdown (Informal)
[Data Augmentation for Rare Symptoms in Vaccine Side-Effect Detection](https://aclanthology.org/2022.bionlp-1.29) (Kim & Nakashole, BioNLP 2022)
ACL