NAP at SemEval-2023 Task 3: Is Less Really More? (Back-)Translation as Data Augmentation Strategies for Detecting Persuasion Techniques
Computation and Language
2023-04-28 v1
Abstract
Persuasion techniques detection in news in a multi-lingual setup is non-trivial and comes with challenges, including little training data. Our system successfully leverages (back-)translation as data augmentation strategies with multi-lingual transformer models for the task of detecting persuasion techniques. The automatic and human evaluation of our augmented data allows us to explore whether (back-)translation aid or hinder performance. Our in-depth analyses indicate that both data augmentation strategies boost performance; however, balancing human-produced and machine-generated data seems to be crucial.
Keywords
Cite
@article{arxiv.2304.14179,
title = {NAP at SemEval-2023 Task 3: Is Less Really More? (Back-)Translation as Data Augmentation Strategies for Detecting Persuasion Techniques},
author = {Neele Falk and Annerose Eichel and Prisca Piccirilli},
journal= {arXiv preprint arXiv:2304.14179},
year = {2023}
}
Comments
14 pages, 17 figures, 11 tables. Accepted at SemEval2023@ACL