LTG at SemEval-2025 Task 10: Optimizing Context for Classification of Narrative Roles

2025/06/06 by Egil Rønningstad, Rønningstad, Egil, Gaurav Singh Negi +1
Computer Science · Social Sciences · #Topic Modeling #Text Readability and Simplification #Computational and Text Analysis Methods

paper · pdf · doi:10.48550/arxiv.2506.05976

Abstract

Our contribution to the SemEval 2025 shared task 10, subtask 1 on entity framing, tackles the challenge of providing the necessary segments from longer documents as context for classification with a masked language model. We show that a simple entity-oriented heuristics for context selection can enable text classification using models with limited context window. Our context selection approach and the XLM-RoBERTa language model is on par with, or outperforms, Supervised Fine-Tuning with larger generative language models.

Citations

• Reducing Distraction in Long-Context Language Models by Focused Learning
• FACT: Examining the Effectiveness of Iterative Context Rewriting for Multi-fact Retrieval
• Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference
• Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation
• UIO at SemEval-2023 Task 12: Multilingual fine-tuning for sentiment classification in low-resource languages
• Large Language Models Can Be Easily Distracted by Irrelevant Context
• Unsupervised Cross-lingual Representation Learning at Scale

Related

• Fane at SemEval-2025 Task 10: Zero-Shot Entity Framing with Large Language Models
• Larger-Context Language Modelling
• Document-Level Event Role Filler Extraction using Multi-Granularity Contextualized Encoding
• Language Models for Text Classification: Is In-Context Learning Enough?
• Generative Context-aware Fine-tuning of Self-supervised Speech Models