Skip to content
conftrace_
2023 SemEval SemEval 2023

TeamAmpa at SemEval-2023 Task 3: Exploring Multilabel and Multilingual RoBERTa Models for Persuasion and Framing Detection

Abstract

AbstractThis paper describes our submission to theSemEval 2023 Task 3 on two subtasks: detectingpersuasion techniques and framing. Bothsubtasks are multi-label classification problems. We present a set of experiments, exploring howto get robust performance across languages usingpre-trained RoBERTa models. We test differentoversampling strategies, a strategy ofadding textual features from predictions obtainedwith related models, and present bothinconclusive and negative results. We achievea robust ranking across languages and subtaskswith our best ranking being nr. 1 for Subtask 3on Spanish.

Authors

Amalie Pauli, Rafael Sarabia, Leon Derczynski, Ira Assent

Topics

Artificial Intelligence > Core AI > Multimodal Learning Machine Learning > Core Methods > Classification Machine Learning > Learning Types > Multi-Label Classification

Keywords

text classification multi-label classification persuasion detection multilingual transformer framing detection
Download PDF

More from SemEval 2023

All SemEval 2023 papers →
garNER at SemEval-2023: Simplified Knowledge Augmentation for Multilingual Complex Named Entity Recognition
D2KLab at SemEval-2023 Task 2: Leveraging T-NER to Develop a Fine-Tuned Multilingual Model for Complex Named Entity Recognition
LTRC at SemEval-2023 Task 6: Experiments with Ensemble Embeddings
UM6P at SemEval-2023 Task 3: News genre classification based on transformers, graph convolution networks and number of sentences
Viettel-AI at SemEval-2023 Task 6: Legal Document Understanding with Longformer for Court Judgment Prediction with Explanation
GunadarmaXBRIN at SemEval-2023 Task 12: Utilization of SVM and AfriBERTa for Monolingual, Multilingual, and Zero-shot Sentiment Analysis in African Languages