构建美国立法文本命名实体识别数据集，支持多级实体抽取
The GELATO Dataset for Legislative NER
- 设计两级标注体系，专用于美联邦立法文本
- RoBERTa表现优于BERT，LLM提升二级实体识别精度
- 适合法律人工智能、政策分析研究者使用
本文提出GELATO（政府、行政、立法及条约本体）数据集，包含第118届美国国会众议院与参议院法案的标注数据。采用新型两级命名实体识别本体对文本进行标注。针对一级实体预测，微调不同架构和规模的Transformer模型（BERT、RoBERTa）；二级实体预测则利用优化提示的大型语言模型（LLM）完成。实验显示，RoBERTa在一级预测中表现优于BERT，而使用LLM作为二级预测器显著提升了整体性能，验证了该模型组合在立法领域命名实体识别或下游任务中的有效性，为未来研究提供可复用的抽取工具。
原文摘要 · Abstract (English)
This paper introduces GELATO (Government, Executive, Legislative, and Treaty Ontology), a dataset of U.S. House and Senate bills from the 118th Congress annotated using a novel two-level named entity recognition ontology designed for U.S. legislative texts. We fine-tune transformer-based models (BERT, RoBERTa) of different architectures and sizes on this dataset for first-level prediction. We then use LLMs with optimized prompts to complete the second level prediction. The strong performance of RoBERTa and relatively weak performance of BERT models, as well as the application of LLMs as second-level predictors, support future research in legislative NER or downstream tasks using these model combinations as extraction tools.
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。