Cross-Lingual Learning vs. Low-Resource Fine-Tuning: A Case Study with Fact-Checking in Turkish

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cekinel, Recep Firat, Karagoz, Pinar, Coltekin, Cagri
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911808645758976
author Cekinel, Recep Firat
Karagoz, Pinar
Coltekin, Cagri
author_facet Cekinel, Recep Firat
Karagoz, Pinar
Coltekin, Cagri
contents The rapid spread of misinformation through social media platforms has raised concerns regarding its impact on public opinion. While misinformation is prevalent in other languages, the majority of research in this field has concentrated on the English language. Hence, there is a scarcity of datasets for other languages, including Turkish. To address this concern, we have introduced the FCTR dataset, consisting of 3238 real-world claims. This dataset spans multiple domains and incorporates evidence collected from three Turkish fact-checking organizations. Additionally, we aim to assess the effectiveness of cross-lingual transfer learning for low-resource languages, with a particular focus on Turkish. We demonstrate in-context learning (zero-shot and few-shot) performance of large language models in this context. The experimental results indicate that the dataset has the potential to advance research in the Turkish language.
format Preprint
id arxiv_https___arxiv_org_abs_2403_00411
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cross-Lingual Learning vs. Low-Resource Fine-Tuning: A Case Study with Fact-Checking in Turkish
Cekinel, Recep Firat
Karagoz, Pinar
Coltekin, Cagri
Computation and Language
The rapid spread of misinformation through social media platforms has raised concerns regarding its impact on public opinion. While misinformation is prevalent in other languages, the majority of research in this field has concentrated on the English language. Hence, there is a scarcity of datasets for other languages, including Turkish. To address this concern, we have introduced the FCTR dataset, consisting of 3238 real-world claims. This dataset spans multiple domains and incorporates evidence collected from three Turkish fact-checking organizations. Additionally, we aim to assess the effectiveness of cross-lingual transfer learning for low-resource languages, with a particular focus on Turkish. We demonstrate in-context learning (zero-shot and few-shot) performance of large language models in this context. The experimental results indicate that the dataset has the potential to advance research in the Turkish language.
title Cross-Lingual Learning vs. Low-Resource Fine-Tuning: A Case Study with Fact-Checking in Turkish
topic Computation and Language
url https://arxiv.org/abs/2403.00411