Skip to content
Review

Extended Overview of HIPE-2026: Evaluating Accurate and Efficient Person-Place Relation Extraction from Multilingual Historical Texts

2026 · Conference and Labs of the Evaluation Forum · pp. 2890-2923 · 12 citations · ⚡ 2 influential · 39 references
Computer Science

TL;DR

Results reveal a wide range of strategies, from state-of-the-art large language models to lightweight task-specific classifiers, and highlight the trade-offs between accuracy, efficiency, and robustness inherent to historical relation extraction at corpus scale.

View source

Similar papers

2026

Few-Shot Prompting with Large Language Models for Multilingual Person-Place Relation Extraction from Historical Documents

The experimental results show that API-based LLM prompting, combined with simple post-processing operations, is competitive for low-resource relation extraction on historical documents, while also raising reproducibility, cost, and data-governance considerations.

Hao-Jie Cao, Zhong-Yuan Han, Xian-Bing Duan · 2 citations
2026

From Frozen Encoders to Multi-Agent LLM Pipelines: An Iterative Journey through Person-Place Relation Extraction in Multilingual Historical Texts

This paper documents the design decisions, failure modes, and key insights behind each strategy, including an honest analysis of the 17-point dev-to-test gap, providing a comprehensive account of iterative NLP system development under data scarcity, class imbalance, and multilingual historical OCR noise.

Pradyuman Singh Shekhawat, Rohan Gupta · 2 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.