KInITVeraAI at SemEval-2023 Task 3: Simple yet Powerful Multilingual Fine-Tuning for Persuasion Techniques Detection
This work addresses the challenge of multilingual persuasion detection for NLP researchers, but it is incremental as it applies existing fine-tuning methods to a specific task.
The paper tackled the problem of detecting persuasion techniques in multilingual text with 23 labels, where data scarcity was an issue for some language-label combinations, by fine-tuning a large multilingual transformer model (XLM-RoBERTa large) with calibrated confidence thresholds, resulting in the best performance on 6 out of 9 languages and competitive results on the others.
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.