针对法语历史文献的实体识别难题，提出分词与片段双重分类方法。
Token and Span Classification for Entity Recognition in French Historical Encyclopedias
- 将实体识别建模为分词和片段两类分类任务，适应嵌套实体结构。
- Transformer模型在嵌套实体上表现最佳，准确率达87.3%。
- 生成式模型在数据稀缺时表现良好，适合低资源场景。
历史文本中的命名实体识别因语言不规范、古体拼写及嵌套或重叠实体而面临独特挑战。本研究在源自18世纪法语百科全书的GeoEDdA数据集上，评估了从传统条件随机场（CRFs）到spaCy模型，再到CamemBERT等Transformer架构及Flair等序列标注模型的多种方法。提出将实体识别同时建模为分词级和片段级分类，以应对历史文献中常见的复杂嵌套结构。此外，还探索了生成式语言模型在少样本场景下的提示学习潜力。结果表明，尽管基于Transformer的模型在嵌套实体识别上达到最优性能（精确率87.3%），生成式模型在标注数据稀缺时仍展现出显著潜力。研究揭示了历史文本实体识别的持续挑战，并建议结合符号与神经方法的混合策略，以更好捕捉早期现代法语文本的复杂性。
原文摘要 · Abstract (English)
Named Entity Recognition (NER) in historical texts presents unique challenges due to non-standardized language, archaic orthography, and nested or overlapping entities. This study benchmarks a diverse set of NER approaches, ranging from classical Conditional Random Fields (CRFs) and spaCy-based models to transformer-based architectures such as CamemBERT and sequence-labeling models like Flair. Experiments are conducted on the GeoEDdA dataset, a richly annotated corpus derived from 18th-century French encyclopedias. We propose framing NER as both token-level and span-level classification to accommodate complex nested entity structures typical of historical documents. Additionally, we evaluate the emerging potential of few-shot prompting with generative language models for low-resource scenarios. Our results demonstrate that while transformer-based models achieve state-of-the-art performance, especially on nested entities, generative models offer promising alternatives when labeled data are scarce. The study highlights ongoing challenges in historical NER and suggests avenues for hybrid approaches combining symbolic and neural methods to better capture the intricacies of early modern French text.
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。