@inproceedings{huang-etal-2022-zydhjh4593,
title = "zydhjh4593@{SMM}4{H}{'}22: A Generic Pre-trained {BERT}-based Framework for Social Media Health Text Classification",
author = "Huang, Chenghao and
Chen, Xiaolu and
Chen, Yuxi and
Wu, Yutong and
Yuan, Weimin and
Wang, Yan and
Zhang, Yanru",
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-1.4",
pages = "11--15",
abstract = "This paper describes our proposed framework for the 10 text classification tasks of Task 1a, 2a, 2b, 3a, 4, 5, 6, 7, 8, and 9, in the Social Media Mining for Health (SMM4H) 2022. According to the pre-trained BERT-based models, various techniques, including regularized dropout, focal loss, exponential moving average, 5-fold cross-validation, ensemble prediction, and pseudo-labeling, are applied for further formulating and improving the generalization performance of our framework. In the evaluation, the proposed framework achieves the 1st place in Task 3a with a 7{\%} higher F1-score than the median, and obtains a 4{\%} higher averaged F1-score than the median in all participating tasks except Task 1a.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2022-zydhjh4593">
<titleInfo>
<title>zydhjh4593@SMM4H’22: A Generic Pre-trained BERT-based Framework for Social Media Health Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chenghao</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaolu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutong</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weimin</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanru</namePart>
<namePart type="family">Zhang</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>This paper describes our proposed framework for the 10 text classification tasks of Task 1a, 2a, 2b, 3a, 4, 5, 6, 7, 8, and 9, in the Social Media Mining for Health (SMM4H) 2022. According to the pre-trained BERT-based models, various techniques, including regularized dropout, focal loss, exponential moving average, 5-fold cross-validation, ensemble prediction, and pseudo-labeling, are applied for further formulating and improving the generalization performance of our framework. In the evaluation, the proposed framework achieves the 1st place in Task 3a with a 7% higher F1-score than the median, and obtains a 4% higher averaged F1-score than the median in all participating tasks except Task 1a.</abstract>
<identifier type="citekey">huang-etal-2022-zydhjh4593</identifier>
<location>
<url>https://aclanthology.org/2022.smm4h-1.4</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>11</start>
<end>15</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T zydhjh4593@SMM4H’22: A Generic Pre-trained BERT-based Framework for Social Media Health Text Classification
%A Huang, Chenghao
%A Chen, Xiaolu
%A Chen, Yuxi
%A Wu, Yutong
%A Yuan, Weimin
%A Wang, Yan
%A Zhang, Yanru
%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 huang-etal-2022-zydhjh4593
%X This paper describes our proposed framework for the 10 text classification tasks of Task 1a, 2a, 2b, 3a, 4, 5, 6, 7, 8, and 9, in the Social Media Mining for Health (SMM4H) 2022. According to the pre-trained BERT-based models, various techniques, including regularized dropout, focal loss, exponential moving average, 5-fold cross-validation, ensemble prediction, and pseudo-labeling, are applied for further formulating and improving the generalization performance of our framework. In the evaluation, the proposed framework achieves the 1st place in Task 3a with a 7% higher F1-score than the median, and obtains a 4% higher averaged F1-score than the median in all participating tasks except Task 1a.
%U https://aclanthology.org/2022.smm4h-1.4
%P 11-15
Markdown (Informal)
[zydhjh4593@SMM4H’22: A Generic Pre-trained BERT-based Framework for Social Media Health Text Classification](https://aclanthology.org/2022.smm4h-1.4) (Huang et al., SMM4H 2022)
ACL
- Chenghao Huang, Xiaolu Chen, Yuxi Chen, Yutong Wu, Weimin Yuan, Yan Wang, and Yanru Zhang. 2022. zydhjh4593@SMM4H’22: A Generic Pre-trained BERT-based Framework for Social Media Health Text Classification. In Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task, pages 11–15, Gyeongju, Republic of Korea. Association for Computational Linguistics.