2025年「查證真相！」AI奇才：融合情感分析強化變換器嵌入，用於新聞文章主觀性偵測

摘要

本文介绍了AI Wizards参与CLEF 2025 CheckThat!实验室任务1：新闻文章中的主观性检测，在单语、多语及零样本设置下对句子进行主观/客观分类。训练/开发数据集涵盖了阿拉伯语、德语、英语、意大利语和保加利亚语；最终评估则引入了更多未见语言（如希腊语、罗马尼亚语、波兰语、乌克兰语）以评估模型的泛化能力。我们的核心策略是通过将辅助模型生成的情感评分与句子表征相结合，增强基于Transformer的分类器性能，旨在超越标准微调方法。我们利用mDeBERTaV3-base、ModernBERT-base（英语）及Llama3.2-1B探索了这种情感增强架构。针对跨语言普遍存在的类别不平衡问题，我们采用了基于开发集优化的决策阈值校准技术。实验结果表明，情感特征的整合显著提升了模型性能，尤其是主观F1分数。该框架使我们在多项排名中位居前列，特别是在希腊语上取得了第一名的佳绩（宏F1 = 0.51）。

English

This paper presents AI Wizards' participation in the CLEF 2025 CheckThat! Lab Task 1: Subjectivity Detection in News Articles, classifying sentences as subjective/objective in monolingual, multilingual, and zero-shot settings. Training/development datasets were provided for Arabic, German, English, Italian, and Bulgarian; final evaluation included additional unseen languages (e.g., Greek, Romanian, Polish, Ukrainian) to assess generalization. Our primary strategy enhanced transformer-based classifiers by integrating sentiment scores, derived from an auxiliary model, with sentence representations, aiming to improve upon standard fine-tuning. We explored this sentiment-augmented architecture with mDeBERTaV3-base, ModernBERT-base (English), and Llama3.2-1B. To address class imbalance, prevalent across languages, we employed decision threshold calibration optimized on the development set. Our experiments show sentiment feature integration significantly boosts performance, especially subjective F1 score. This framework led to high rankings, notably 1st for Greek (Macro F1 = 0.51).

2025年「查證真相！」AI奇才：融合情感分析強化變換器嵌入，用於新聞文章主觀性偵測

AI Wizards at CheckThat! 2025: Enhancing Transformer-Based Embeddings with Sentiment for Subjectivity Detection in News Articles

摘要

Support