# NAP at SemEval-2023 Task 3: Is Less Really More? (Back-)Translation as Data Augmentation Strategies for Detecting Persuasion Techniques

arXiv: https://arxiv.org/abs/2304.14179 · HTML: https://mlsanity.com/paper/2304.14179/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 29 references that are in the map.
- First posted on arXiv 27 Apr 2023.

## Builds on (most cited first, 9 of 9)

- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [AdapterHub: A Framework for Adapting Transformers](https://mlsanity.com/paper/2007.07779/) (2020)
- [Marian: Fast Neural Machine Translation in C++](https://mlsanity.com/paper/1804.00344/) (2018)
- [Efficient Few-Shot Learning Without Prompts](https://mlsanity.com/paper/2209.11055/) (2022)
- [SemEval-2020 Task 11: Detection of Propaganda Techniques in News Articles](https://mlsanity.com/paper/2009.02696/) (2020)
- [SemEval-2021 Task 6: Detection of Persuasion Techniques in Texts and Images](https://mlsanity.com/paper/2105.09284/) (2021)
- [Findings of the NLP4IF-2019 Shared Task on Fine-Grained Propaganda Detection](https://mlsanity.com/paper/1910.09982/) (2019)
- [ApplicaAI at SemEval-2020 Task 11: On RoBERTa-CRF, Span CLS and Whether Self-Training Helps Them](https://mlsanity.com/paper/2005.07934/) (2020)
- [aschern at SemEval-2020 Task 11: It Takes Three to Tango: RoBERTa, CRF, and Transfer Learning](https://mlsanity.com/paper/2008.02837/) (2020)

## Built on by (most cited first, 1 of 1)

- [Comparison between parameter-efficient techniques and full fine-tuning: A case study on multilingual news article classification](https://mlsanity.com/paper/2308.07282/) (2023)

## Abstract (arXiv)

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.