LIIR at SemEval-2021 task 6: Detection of Persuasion Techniques In Texts and Images using CLIP features
Not on the map. Why?
Abstract (arXiv)
We describe our approach for SemEval-2021 task 6 on detection of persuasion techniques in multimodal content (memes). Our system combines pretrained multimodal models (CLIP) and chained classifiers. Also, we propose to enrich the data by a data augmentation technique. Our submission achieves a rank of 8/16 in terms of F1-micro and 9/16 with F1-macro on the test set.
Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 10 of its 28 references that are in the map. First posted on arXiv 31 May 2021.
Builds on
10 of 28 references.
References · 10
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,588
- 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
- 2020The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memescited by 486
- 2019Facebook FAIR's WMT19 News Translation Task Submissioncited by 179
- 2020SemEval-2020 Task 11: Detection of Propaganda Techniques in News Articlescited by 80
- 2020A Survey on Computational Propaganda Detectioncited by 69
- 2021SemEval-2021 Task 6: Detection of Persuasion Techniques in Texts and Imagescited by 49
- 2020Detecting Hateful Memes Using a Multimodal Deep Ensemblecited by 30
- 2020LIIR at SemEval-2020 Task 12: A Cross-Lingual Augmentation Approach for Multilingual Offensive Language Identificationcited by 5
- 2018An Unsupervised Approach for Aspect Category Detection Using Soft Cosine Similarity Measurecited by 3
Built on by
Not cited yet.