AnnoABSA是首个支持全链路ABSA的在线标注工具，用LLM增强建议提升标注效率。
AnnoABSA: A Web-Based Annotation Tool for Aspect-Based Sentiment Analysis with Retrieval-Augmented Suggestions
- 基于检索增强生成，自动提供上下文相关标注建议
- 每轮推荐10个已标注相似样本，随标注推进建议更精准
- 开源免费，适合做情感分析数据构建的研究与开发者
我们提出AnnoABSA，首个支持端到端方面级情感分析（ABSA）任务的网页标注工具。该工具高度可配置，可灵活定义情感要素和任务需求。除手动标注外，系统提供可选的大型语言模型（LLM）检索增强生成（RAG）建议，在人机协同模式下为标注者提供上下文感知辅助，始终由人工掌控。为持续提升预测质量，系统会检索前10个最相似的已标注样本，并作为少样本示例加入提示中，使建议随标注进程逐步优化。AnnoABSA以MIT许可证开源，免费使用且易于扩展，适用于研究与实际应用。
原文摘要 · Abstract (English)
We introduce AnnoABSA, the first web-based annotation tool to support the full spectrum of Aspect-Based Sentiment Analysis (ABSA) tasks. The tool is highly customizable, enabling flexible configuration of sentiment elements and task-specific requirements. Alongside manual annotation, AnnoABSA provides optional Large Language Model (LLM)-based retrieval-augmented generation (RAG) suggestions that offer context-aware assistance in a human-in-the-loop approach, keeping the human annotator in control. To improve prediction quality over time, the system retrieves the ten most similar examples that are already annotated and adds them as few-shot examples in the prompt, ensuring that suggestions become increasingly accurate as the annotation process progresses. Released as open-source software under the MIT License, AnnoABSA is freely accessible and easily extendable for research and practical applications.
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。