UoB-NLP 在 SemEval-2025 任务 11：利用适配器进行多语言与跨语言情感检测
UoB-NLP at SemEval-2025 Task 11: Leveraging Adapters for Multilingual and Cross-Lingual Emotion Detection
AI总结：
本文提出利用适配器微调多语言预训练模型进行多语言与跨语言情感检测，目标语言就绪任务适配器在低资源非洲语言上表现最佳，并在多项 SemEval-2025 任务中取得领先排名。
摘要：
自然语言处理中的情感检测因人类情感的复杂性和语言多样性而成为一项具有挑战性的任务。尽管在高资源语言中已取得显著进展，低资源语言中的情感检测仍未被充分探索。在本工作中，我们通过利用基于适配器的微调与多语言预训练语言模型来解决多语言和跨语言情感检测问题。适配器在保持预训练模型权重固定的同时引入少量可训练参数，提供了一种参数高效的自适应方法。我们实验了不同的适配器调优策略，包括仅任务适配器、目标语言就绪的任务适配器以及基于语系的适配器。我们的结果表明，目标语言就绪的任务适配器取得了最佳整体性能，尤其对于低资源非洲语言，我们的团队在 Track A 中 Tigrinya 语排名第 7，Kinyarwanda 语排名第 8。在 Track C 中，我们的系统在 Amharic 语上排名第 3，在 Oromo、Tigrinya、Kinyarwanda、Hausa 和 Igbo 语上排名第 4。尽管我们的模型参数量显著更少，我们的方法在 11 种语言上超越了大语言模型，并在另外四种语言上与其性能相当。此外，我们发现与对每种语言进行完整微调相比，基于适配器的模型在保留跨语言迁移能力的同时需要更少的计算资源。
英文摘要：
Emotion detection in natural language processing is a challenging task due to the complexity of human emotions and linguistic diversity. While significant progress has been made in high-resource languages, emotion detection in low-resource languages remains underexplored. In this work, we address multilingual and cross-lingual emotion detection by leveraging adapter-based fine-tuning with multilingual pre-trained language models. Adapters introduce a small number of trainable parameters while keeping the pre-trained model weights fixed, offering a parameter-efficient approach to adaptation. We experiment with different adapter tuning strategies, including task-only adapters, target-language-ready task adapters, and language-family-based adapters. Our results show that target-language-ready task adapters achieve the best overall performance, particularly for low-resource African languages with our team ranking 7th for Tigrinya, and 8th for Kinyarwanda in Track A. In Track C, our system ranked 3rd for Amharic, and 4th for Oromo, Tigrinya, Kinyarwanda, Hausa, and Igbo. Our approach outperforms large language models in 11 languages and matches their performance in four others, despite our models having significantly fewer parameters. Furthermore, we find that adapter-based models retain cross-linguistic transfer capabilities while requiring fewer computational resources compared to full fine-tuning for each language.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
