@inproceedings{palmer-etal-2022-chaai,
title = "{CHAAI}@{SMM}4{H}{'}22: {R}o{BERT}a, {GPT}-2 and Sampling - An interesting concoction",
author = "Palmer, Christopher and
Khademi Habibabadi, Sedigheh and
Javed, Muhammad and
Dimaguila, Gerardo Luis and
Buttery, Jim",
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-1.24",
pages = "81--84",
abstract = "This paper describes the approaches to the SMM4H 2022 Shared Tasks that were taken by our team for tasks 1 and 6. Task 6 was the {``}Classification of tweets which indicate self-reported COVID-19 vaccination status (in English){''}. The best test F1 score was 0.82 using a CT-BERT model, which exceeded the median test F1 score of 0.77, and was close to the 0.83 F1 score of the SMM4H baseline model. Task 1 was described as the {``}Classification, detection and normalization of Adverse Events (AE) mentions in tweets (in English){''}. We undertook task 1a, and with a RoBERTa-base model achieved an F1 Score of 0.61 on test data, which exceeded the mean test F1 for the task of 0.56.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="palmer-etal-2022-chaai">
<titleInfo>
<title>CHAAI@SMM4H’22: RoBERTa, GPT-2 and Sampling - An interesting concoction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sedigheh</namePart>
<namePart type="family">Khademi Habibabadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Javed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerardo</namePart>
<namePart type="given">Luis</namePart>
<namePart type="family">Dimaguila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jim</namePart>
<namePart type="family">Buttery</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>
<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 the approaches to the SMM4H 2022 Shared Tasks that were taken by our team for tasks 1 and 6. Task 6 was the “Classification of tweets which indicate self-reported COVID-19 vaccination status (in English)”. The best test F1 score was 0.82 using a CT-BERT model, which exceeded the median test F1 score of 0.77, and was close to the 0.83 F1 score of the SMM4H baseline model. Task 1 was described as the “Classification, detection and normalization of Adverse Events (AE) mentions in tweets (in English)”. We undertook task 1a, and with a RoBERTa-base model achieved an F1 Score of 0.61 on test data, which exceeded the mean test F1 for the task of 0.56.</abstract>
<identifier type="citekey">palmer-etal-2022-chaai</identifier>
<location>
<url>https://aclanthology.org/2022.smm4h-1.24</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>81</start>
<end>84</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CHAAI@SMM4H’22: RoBERTa, GPT-2 and Sampling - An interesting concoction
%A Palmer, Christopher
%A Khademi Habibabadi, Sedigheh
%A Javed, Muhammad
%A Dimaguila, Gerardo Luis
%A Buttery, Jim
%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 palmer-etal-2022-chaai
%X This paper describes the approaches to the SMM4H 2022 Shared Tasks that were taken by our team for tasks 1 and 6. Task 6 was the “Classification of tweets which indicate self-reported COVID-19 vaccination status (in English)”. The best test F1 score was 0.82 using a CT-BERT model, which exceeded the median test F1 score of 0.77, and was close to the 0.83 F1 score of the SMM4H baseline model. Task 1 was described as the “Classification, detection and normalization of Adverse Events (AE) mentions in tweets (in English)”. We undertook task 1a, and with a RoBERTa-base model achieved an F1 Score of 0.61 on test data, which exceeded the mean test F1 for the task of 0.56.
%U https://aclanthology.org/2022.smm4h-1.24
%P 81-84
Markdown (Informal)
[CHAAI@SMM4H’22: RoBERTa, GPT-2 and Sampling - An interesting concoction](https://aclanthology.org/2022.smm4h-1.24) (Palmer et al., SMM4H 2022)
ACL
- Christopher Palmer, Sedigheh Khademi Habibabadi, Muhammad Javed, Gerardo Luis Dimaguila, and Jim Buttery. 2022. CHAAI@SMM4H’22: RoBERTa, GPT-2 and Sampling - An interesting concoction. In Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task, pages 81–84, Gyeongju, Republic of Korea. Association for Computational Linguistics.