@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://preview.aclanthology.org/fix-sig-urls/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."
}