Saved in:
Bibliographic Details
Main Authors: Hromadka, Timo, Smolen, Timotej, Remis, Tomas, Pecher, Branislav, Srba, Ivan
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2304.11924
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916279751802880
author Hromadka, Timo
Smolen, Timotej
Remis, Tomas
Pecher, Branislav
Srba, Ivan
author_facet Hromadka, Timo
Smolen, Timotej
Remis, Tomas
Pecher, Branislav
Srba, Ivan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2304_11924
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle KInITVeraAI at SemEval-2023 Task 3: Simple yet Powerful Multilingual Fine-Tuning for Persuasion Techniques Detection
Hromadka, Timo
Smolen, Timotej
Remis, Tomas
Pecher, Branislav
Srba, Ivan
Computation and Language
Machine Learning
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.
title KInITVeraAI at SemEval-2023 Task 3: Simple yet Powerful Multilingual Fine-Tuning for Persuasion Techniques Detection
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2304.11924