2025
ACL
ACL 2025
TueCL at SemEval-2025 Task 1: Image-Augmented Prompting and Multimodal Reasoning for Enhanced Idiom Understanding
Abstract
AbstractThis paper presents our approach for SemEval-2025 Task 1, Advancing Multimodal Idiomaticity Representation (AdMIRe), which focuses on idiom image ranking via semantic similarity. We explore multiple strategies, including neural networks on extracted embeddings and Siamese networks with triplet loss. A key component of our methodology is the application of advanced prompt engineeringtechniques within multimodal in-context learning (ManyICL), leveraging GPT-4o, CLIP.Our experiments demonstrate that structured and optimized prompts significantly enhancethe model’s ability to interpret idiomatic expressions in a multimodal setting.
🌉
Interdisciplinary Bridge
— Artificial Intelligence and Deep Learning and Machine Learning
🧭
Keyword Pioneer
— idiom understanding
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Robotics, Speech & Audio
Authors
Topics
Artificial Intelligence > Core AI > Multimodal Learning
Artificial Intelligence > Learning Paradigms > Few-Shot Learning
Machine Learning > Core Methods > Classification
Machine Learning > Core Methods > Representation Learning
Machine Learning > Core Methods > Metric Learning
Deep Learning > Architectures > Transformers
Deep Learning > Architectures > Neural Networks
Deep Learning > Techniques > Pretraining
Machine Learning > Learning Types > Few-Shot Learning