Publication Details
KInITVeraAI at SemEval-2023 Task 3: Simple yet Powerful Multilingual Fine-Tuning for Persuasion Techniques Detection
multilingual persuasion technique detection, fine-tuning, SemEval
This paper presents the best-performing solution to the SemEval 2023 Task 3 on the subtask 3 dedicated to persuasion techniques detection. Due to a high multilingual character of the input data and a large number of 23 predicted labels (causing a lack of labelled data for some language-label combinations), we opted for fine-tuning pre-trained transformer-based language models. Conducting multiple experiments, we find the best configuration, which consists of large multilingual model (XLM-RoBERTa large) trained jointly on all input data, with carefully calibrated confidence thresholds for seen and surprise languages separately. Our final system performed the best on 6 out of 9 languages (including two surprise languages) and achieved highly competitive results on the remaining three languages.
@inproceedings{BUT185334,
author="HROMÁDKA, T. and SMOLEŇ, T. and REMIŠ, T. and PECHER, B. and SRBA, I.",
title="KInITVeraAI at SemEval-2023 Task 3: Simple yet Powerful Multilingual Fine-Tuning for Persuasion Techniques Detection",
booktitle="17th International Workshop on Semantic Evaluation, SemEval 2023 - Proceedings of the Workshop",
year="2023",
pages="629--637",
publisher="Association for Computational Linguistics",
address="Toronto",
doi="10.18653/v1/2023.semeval-1.86",
isbn="978-1-959429-99-9",
url="https://aclanthology.org/2023.semeval-1.86/"
}