Document Retrieval and Claim Verification to Mitigate COVID-19 Misinformation

Sundriyal, Megha; Malhotra, Ganeshan; Akhtar, Md. Shad; Sengupta, Shamik; Fano, Andrew; Chakraborty, Tanmoy

doi:10.18653/v1/2022.constraint-1.8

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While most existing methods to combat fake news are primarily tailored for English (Levy et al, 2014;Lippi and Torroni, 2015;Sundriyal et al, , 2022b, in recent times, there has been a surge in interest regarding the advancement of factchecking techniques for various other languages. ClaimRank (Jaradat et al, 2018) introduced an online system to identify sentences containing checkworthy claims in Arabic and English.…”

Section: Related Workmentioning

confidence: 99%

Lost in Translation, Found in Spans: Identifying Claims in Multilingual Social Media

Mittal,

Sundriyal,

Nakov

2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Claim span identification (CSI) is an important step in fact-checking pipelines, aiming to identify text segments that contain a checkworthy claim or assertion in a social media post. Despite its importance to journalists and human fact-checkers, it remains a severely understudied problem, and the scarce research on this topic so far has only focused on English.Here we aim to bridge this gap by creating a novel dataset, X-CLAIM, consisting of 7K realworld claims collected from numerous social media platforms in five Indian languages and English. We report strong baselines with stateof-the-art encoder-only language models (e.g., XLM-R) and we demonstrate the benefits of training on multiple languages over alternative cross-lingual transfer methods such as zeroshot transfer, or training on translated data, from a high-resource language such as English. We evaluate generative large language models from the GPT series using prompting methods on the X-CLAIM dataset and we find that they underperform the smaller encoder-only language models for low-resource languages. 1 † Major part of this work was done during a research internship at MBZUAI.

show abstract

Section: Related Workmentioning

confidence: 99%