@inproceedings{he-etal-2022-zhegu,
title = "Zhegu@{SMM}4{H}-2022: The Pre-training Tweet {\&} Claim Matching Makes Your Prediction Better",
author = "He, Pan and
YuZe, Chen 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-1.11",
pages = "38--41",
abstract = "SMM4H-2022 (CITATION) Task 2 is to detect whether containing premise in the tweets of users about COVID-19 on the social medias or their stances for the claims. In this paper, we propose \textbf{T}weet \textbf{C}laim \textbf{M}atching (\textbf{TCM}), which is a new pre-training task constructed by the tweets and claims similarly to Next Sentence Prediction (NSP). We first continue to pre-train the standard pre-trained language models on the labelled dataset and then fine-tune them for obtaining better performance. Compared with the solid baseline (CITATION), we achieve the absolute improvement of 7.9{\%} in Task 2a and obtain the SOTA results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2022-zhegu">
<titleInfo>
<title>Zhegu@SMM4H-2022: The Pre-training Tweet & Claim Matching Makes Your Prediction Better</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">YuZe</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>SMM4H-2022 (CITATION) Task 2 is to detect whether containing premise in the tweets of users about COVID-19 on the social medias or their stances for the claims. In this paper, we propose Tweet Claim Matching (TCM), which is a new pre-training task constructed by the tweets and claims similarly to Next Sentence Prediction (NSP). We first continue to pre-train the standard pre-trained language models on the labelled dataset and then fine-tune them for obtaining better performance. Compared with the solid baseline (CITATION), we achieve the absolute improvement of 7.9% in Task 2a and obtain the SOTA results.</abstract>
<identifier type="citekey">he-etal-2022-zhegu</identifier>
<location>
<url>https://aclanthology.org/2022.smm4h-1.11</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>38</start>
<end>41</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Zhegu@SMM4H-2022: The Pre-training Tweet & Claim Matching Makes Your Prediction Better
%A He, Pan
%A YuZe, Chen
%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 he-etal-2022-zhegu
%X SMM4H-2022 (CITATION) Task 2 is to detect whether containing premise in the tweets of users about COVID-19 on the social medias or their stances for the claims. In this paper, we propose Tweet Claim Matching (TCM), which is a new pre-training task constructed by the tweets and claims similarly to Next Sentence Prediction (NSP). We first continue to pre-train the standard pre-trained language models on the labelled dataset and then fine-tune them for obtaining better performance. Compared with the solid baseline (CITATION), we achieve the absolute improvement of 7.9% in Task 2a and obtain the SOTA results.
%U https://aclanthology.org/2022.smm4h-1.11
%P 38-41
Markdown (Informal)
[Zhegu@SMM4H-2022: The Pre-training Tweet & Claim Matching Makes Your Prediction Better](https://aclanthology.org/2022.smm4h-1.11) (He et al., SMM4H 2022)
ACL