@inproceedings{sundriyal-etal-2023-chaos,
title = "From Chaos to Clarity: Claim Normalization to Empower Fact-Checking",
author = "Sundriyal, Megha and
Chakraborty, Tanmoy and
Nakov, Preslav",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.439",
doi = "10.18653/v1/2023.findings-emnlp.439",
pages = "6594--6609",
abstract = "With the proliferation of social media platforms, users are exposed to vast information, including posts containing misleading claims. However, the pervasive noise inherent in these posts presents a challenge in identifying precise and prominent claims that require verification. Extracting the core assertions from such posts is arduous and time-consuming. We introduce a novel task, called Claim Normalization ($\textit{aka ClaimNorm}$) that aims to decompose complex and noisy social media posts into more straightforward and understandable forms, termed $\textit{normalized claims}$. We propose $\texttt{CACN}$ , a pioneering approach that leverages chain-of-thought and claim check-worthiness estimation, mimicking human reasoning processes, to comprehend intricate claims. Moreover, we capitalize on large language models{'} powerful in-context learning abilities to provide guidance and improve the claim normalization process. To evaluate the effectiveness of our proposed model, we meticulously compile a comprehensive real-world dataset, $\texttt{CLAN}$, comprising more than $6k$ instances of social media posts alongside their respective normalized claims. Experimentation demonstrates that $\texttt{CACN}$ outperforms several baselines across various evaluation measures. A rigorous error analysis validates $\texttt{CACN}${`}s capabilities and pitfalls. We release our dataset and code at https://github.com/LCS2-IIITD/CACN-EMNLP-2023.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sundriyal-etal-2023-chaos">
<titleInfo>
<title>From Chaos to Clarity: Claim Normalization to Empower Fact-Checking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Megha</namePart>
<namePart type="family">Sundriyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the proliferation of social media platforms, users are exposed to vast information, including posts containing misleading claims. However, the pervasive noise inherent in these posts presents a challenge in identifying precise and prominent claims that require verification. Extracting the core assertions from such posts is arduous and time-consuming. We introduce a novel task, called Claim Normalization (aka ClaimNorm) that aims to decompose complex and noisy social media posts into more straightforward and understandable forms, termed normalized claims. We propose CACN , a pioneering approach that leverages chain-of-thought and claim check-worthiness estimation, mimicking human reasoning processes, to comprehend intricate claims. Moreover, we capitalize on large language models’ powerful in-context learning abilities to provide guidance and improve the claim normalization process. To evaluate the effectiveness of our proposed model, we meticulously compile a comprehensive real-world dataset, CLAN, comprising more than 6k instances of social media posts alongside their respective normalized claims. Experimentation demonstrates that CACN outperforms several baselines across various evaluation measures. A rigorous error analysis validates CACN‘s capabilities and pitfalls. We release our dataset and code at https://github.com/LCS2-IIITD/CACN-EMNLP-2023.</abstract>
<identifier type="citekey">sundriyal-etal-2023-chaos</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.439</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.439</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>6594</start>
<end>6609</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Chaos to Clarity: Claim Normalization to Empower Fact-Checking
%A Sundriyal, Megha
%A Chakraborty, Tanmoy
%A Nakov, Preslav
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F sundriyal-etal-2023-chaos
%X With the proliferation of social media platforms, users are exposed to vast information, including posts containing misleading claims. However, the pervasive noise inherent in these posts presents a challenge in identifying precise and prominent claims that require verification. Extracting the core assertions from such posts is arduous and time-consuming. We introduce a novel task, called Claim Normalization (aka ClaimNorm) that aims to decompose complex and noisy social media posts into more straightforward and understandable forms, termed normalized claims. We propose CACN , a pioneering approach that leverages chain-of-thought and claim check-worthiness estimation, mimicking human reasoning processes, to comprehend intricate claims. Moreover, we capitalize on large language models’ powerful in-context learning abilities to provide guidance and improve the claim normalization process. To evaluate the effectiveness of our proposed model, we meticulously compile a comprehensive real-world dataset, CLAN, comprising more than 6k instances of social media posts alongside their respective normalized claims. Experimentation demonstrates that CACN outperforms several baselines across various evaluation measures. A rigorous error analysis validates CACN‘s capabilities and pitfalls. We release our dataset and code at https://github.com/LCS2-IIITD/CACN-EMNLP-2023.
%R 10.18653/v1/2023.findings-emnlp.439
%U https://aclanthology.org/2023.findings-emnlp.439
%U https://doi.org/10.18653/v1/2023.findings-emnlp.439
%P 6594-6609
Markdown (Informal)
[From Chaos to Clarity: Claim Normalization to Empower Fact-Checking](https://aclanthology.org/2023.findings-emnlp.439) (Sundriyal et al., Findings 2023)
ACL