Abstract
This paper describes our submission to the CheckThat! Lab at CLEF 2021, where we participated in Subtask 1A (check-worthy claim detection) in Arabic. We introduce our approach to estimate the checkworthiness of tweets as a ranking task. In our approach, we propose to fine-tune state-of-art transformer based models for Arabic such as AraBERTv0.2-base as well as to leverage additional training data from last year's shared task (CheckThat! Lab 2020) along with the dataset provided this year. According to the official evaluation, our submission obtained a joint 4th position in the competition where seven other groups participated.
Licence information
This item is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
Attribution 3.0 United States
Copyright statements
© 2021 The Author(s). CEUR Workshop Proceedings