@inproceedings{karimi-flek-2022-caisa,
title = "{CAISA}@{SMM}4{H}{'}22: Robust Cross-Lingual Detection of Disease Mentions on Social Media with Adversarial Methods",
author = "Karimi, Akbar and
Flek, Lucie",
editor = "Gonzalez-Hernandez, Graciela and
Weissenbacher, Davy",
booktitle = "Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop {\&} Shared Task",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.smm4h-1.45",
pages = "168--170",
abstract = "We propose adversarial methods for increasing the robustness of disease mention detection on social media. Our method applies adversarial data augmentation on the input and the embedding spaces to the English BioBERT model. We evaluate our method in the SocialDisNER challenge at SMM4H{'}22 on an annotated dataset of disease mentions in Spanish tweets. We find that both methods outperform a heuristic vocabulary-based baseline by a large margin. Additionally, utilizing the English BioBERT model shows a strong performance and outperforms the data augmentation methods even when applied to the Spanish dataset, which has a large amount of data, while augmentation methods show a significant advantage in a low-data setting.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="karimi-flek-2022-caisa">
<titleInfo>
<title>CAISA@SMM4H’22: Robust Cross-Lingual Detection of Disease Mentions on Social Media with Adversarial Methods</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akbar</namePart>
<namePart type="family">Karimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucie</namePart>
<namePart type="family">Flek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Graciela</namePart>
<namePart type="family">Gonzalez-Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davy</namePart>
<namePart type="family">Weissenbacher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose adversarial methods for increasing the robustness of disease mention detection on social media. Our method applies adversarial data augmentation on the input and the embedding spaces to the English BioBERT model. We evaluate our method in the SocialDisNER challenge at SMM4H’22 on an annotated dataset of disease mentions in Spanish tweets. We find that both methods outperform a heuristic vocabulary-based baseline by a large margin. Additionally, utilizing the English BioBERT model shows a strong performance and outperforms the data augmentation methods even when applied to the Spanish dataset, which has a large amount of data, while augmentation methods show a significant advantage in a low-data setting.</abstract>
<identifier type="citekey">karimi-flek-2022-caisa</identifier>
<location>
<url>https://aclanthology.org/2022.smm4h-1.45</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>168</start>
<end>170</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CAISA@SMM4H’22: Robust Cross-Lingual Detection of Disease Mentions on Social Media with Adversarial Methods
%A Karimi, Akbar
%A Flek, Lucie
%Y Gonzalez-Hernandez, Graciela
%Y Weissenbacher, Davy
%S Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F karimi-flek-2022-caisa
%X We propose adversarial methods for increasing the robustness of disease mention detection on social media. Our method applies adversarial data augmentation on the input and the embedding spaces to the English BioBERT model. We evaluate our method in the SocialDisNER challenge at SMM4H’22 on an annotated dataset of disease mentions in Spanish tweets. We find that both methods outperform a heuristic vocabulary-based baseline by a large margin. Additionally, utilizing the English BioBERT model shows a strong performance and outperforms the data augmentation methods even when applied to the Spanish dataset, which has a large amount of data, while augmentation methods show a significant advantage in a low-data setting.
%U https://aclanthology.org/2022.smm4h-1.45
%P 168-170
Markdown (Informal)
[CAISA@SMM4H’22: Robust Cross-Lingual Detection of Disease Mentions on Social Media with Adversarial Methods](https://aclanthology.org/2022.smm4h-1.45) (Karimi & Flek, SMM4H 2022)
ACL