用大模型统一处理多领域多语言的情感四元组抽取。
Multi-domain Multilingual Sentiment Analysis in Industry: Predicting Aspect-based Opinion Quadruples
- 用单个微调模型同时应对多领域、多语言的四元组识别。
- 性能接近专用模型，但显著降低运维复杂度。
- 适合工业界构建通用情感分析系统的技术参考。
本文探讨了在真实场景中利用大语言模型（LLMs）设计基于方面的情感分析系统。研究聚焦于四元组意见抽取——从跨领域、跨语言的文本数据中识别方面类别、情感极性、目标实体和观点表达。我们探究单一微调模型能否有效同时处理多个领域特异性分类体系。实验表明，联合多领域模型的性能可媲美专用单领域模型，同时大幅降低运营复杂性。此外，论文还分享了处理非提取式预测及评估各类失败模式的经验，为构建基于LLM的结构化预测系统提供实践指导。
原文摘要 · Abstract (English)
This paper explores the design of an aspect-based sentiment analysis system using large language models (LLMs) for real-world use. We focus on quadruple opinion extraction -- identifying aspect categories, sentiment polarity, targets, and opinion expressions from text data across different domains and languages. We investigate whether a single fine-tuned model can effectively handle multiple domain-specific taxonomies simultaneously. We demonstrate that a combined multi-domain model achieves performance comparable to specialized single-domain models while reducing operational complexity. We also share lessons learned for handling non-extractive predictions and evaluating various failure modes when developing LLM-based systems for structured prediction tasks.
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。