CLCVJun 1, 2021

Volta at SemEval-2021 Task 6: Towards Detecting Persuasive Texts and Images using Textual and Multimodal Ensemble

arXiv:2106.00240v1711 citations
Originality Synthesis-oriented
AI Analysis

This addresses the challenge of identifying persuasive content in online memes for social media analysis, but it is incremental as it builds on existing BERT and ensemble methods.

The paper tackled the problem of detecting persuasive techniques in memes by proposing a transfer learning approach with BERT-based models and ensembles across modalities, achieving F1-scores of 57.0, 48.2, and 52.1 in three subtasks.

Memes are one of the most popular types of content used to spread information online. They can influence a large number of people through rhetorical and psychological techniques. The task, Detection of Persuasion Techniques in Texts and Images, is to detect these persuasive techniques in memes. It consists of three subtasks: (A) Multi-label classification using textual content, (B) Multi-label classification and span identification using textual content, and (C) Multi-label classification using visual and textual content. In this paper, we propose a transfer learning approach to fine-tune BERT-based models in different modalities. We also explore the effectiveness of ensembles of models trained in different modalities. We achieve an F1-score of 57.0, 48.2, and 52.1 in the corresponding subtasks.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes