UPV at CheckThat! 2021: Mitigating Cultural Differences for Identifying Multilingual Check-worthy Claims

TL;DR

This paper explores multilingual check-worthy claim detection and proposes using language identification as an auxiliary task to reduce cultural bias, demonstrating performance improvements in a multilingual tweet dataset.

Contribution

It introduces a joint training approach combining language identification with claim detection to mitigate cultural bias in multilingual fact-checking.

Findings

Joint training improves detection performance for some languages.

Multilingual representations help address cultural bias.

Language identification as an auxiliary task benefits multilingual claim detection.

Abstract

Identifying check-worthy claims is often the first step of automated fact-checking systems. Tackling this task in a multilingual setting has been understudied. Encoding inputs with multilingual text representations could be one approach to solve the multilingual check-worthiness detection. However, this approach could suffer if cultural bias exists within the communities on determining what is check-worthy.In this paper, we propose a language identification task as an auxiliary task to mitigate unintended bias.With this purpose, we experiment joint training by using the datasets from CLEF-2021 CheckThat!, that contain tweets in English, Arabic, Bulgarian, Spanish and Turkish. Our results show that joint training of language identification and check-worthy claim detection tasks can provide performance gains for some of the selected languages.