用大模型少样本检测文本情绪,多标签任务表现优异。
Few-shot text-based emotion detection
- 结合大模型与少样本提示/微调策略
- 英语集上F1宏值达0.7546,埃马库瓦语集第一
- 适合低资源语言情绪分析研究者参考
本文介绍布加勒斯特大学NLP团队在SemEval 2025工作坊第11项任务——弥合文本情绪检测差距中的方法。我们主要基于Gemini、Qwen和DeepSeek等大模型,采用少样本提示或微调进行实验。最终系统在多标签情绪检测赛道(赛道A)中,英语子集取得F1-macro为0.7546(96支队伍中排名第26),葡萄牙语(莫桑比克)子集得分为0.1727(36支队伍中排名第35),埃马库瓦语子集得分为0.325(31支队伍中排名第一)。
原文摘要 · Abstract (English)
This paper describes the approach of the Unibuc - NLP team in tackling the SemEval 2025 Workshop, Task 11: Bridging the Gap in Text-Based Emotion Detection. We mainly focused on experiments using large language models (Gemini, Qwen, DeepSeek) with either few-shot prompting or fine-tuning. With our final system, for the multi-label emotion detection track (track A), we got an F1-macro of $0.7546$ (26/96 teams) for the English subset, $0.1727$ (35/36 teams) for the Portuguese (Mozambican) subset and $0.325$ (\textbf{1}/31 teams) for the Emakhuwa subset.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。