Named Entity Recognition of Historical Texts via Large Language Model

TL;DR

This paper investigates the use of large language models for named entity recognition in historical texts, demonstrating promising zero-shot and few-shot performance despite data scarcity and language variability.

Contribution

It explores applying LLMs to historical NER tasks using minimal training data, highlighting their potential as an alternative to supervised methods in low-resource settings.

Findings

LLMs achieve reasonably strong NER performance on historical texts.

Performance is below supervised models but still promising.

Zero-shot and few-shot prompting are effective in low-resource scenarios.

Abstract

Large language models (LLMs) have demonstrated remarkable versatility across a wide range of natural language processing tasks and domains. One such task is Named Entity Recognition (NER), which involves identifying and classifying proper names in text, such as people, organizations, locations, dates, and other specific entities. NER plays a crucial role in extracting information from unstructured textual data, enabling downstream applications such as information retrieval from unstructured text. Traditionally, NER is addressed using supervised machine learning approaches, which require large amounts of annotated training data. However, historical texts present a unique challenge, as the annotated datasets are often scarce or nonexistent, due to the high cost and expertise required for manual labeling. In addition, the variability and noise inherent in historical language, such as inconsistent spelling and archaic vocabulary, further complicate the development of reliable NER systems for these sources. In this study, we explore the feasibility of applying LLMs to NER in historical documents using zero-shot and few-shot prompting strategies, which require little to no task-specific training data. Our experiments, conducted on the HIPE-2022 (Identifying Historical People, Places and other Entities) dataset, show that LLMs can achieve reasonably strong performance on NER tasks in this setting. While their performance falls short of fully supervised models trained on domain-specific annotations, the results are nevertheless promising. These findings suggest that LLMs offer a viable and efficient alternative for information extraction in low-resource or historically significant corpora, where traditional supervised methods are infeasible.