Adapting PromptORE for Modern History: Information Extraction from Hispanic Monarchy Documents of the XVIth Century

TL;DR

This paper adapts PromptORE for extracting relations from 16th-century Spanish Inquisition documents by fine-tuning transformer models and engineering prompts, significantly improving accuracy over standard methods.

Contribution

It introduces a biasing technique through fine-tuning and prompt engineering to enhance relation extraction in historical Spanish texts, addressing entity placement and gender issues.

Findings

Up to 50% accuracy improvement with Biased PromptORE

Effective handling of complex entity placements and gender issues

Validated by expert assessments and benchmark evaluations

Abstract

Semantic relations among entities are a widely accepted method for relation extraction. PromptORE (Prompt-based Open Relation Extraction) was designed to improve relation extraction with Large Language Models on generalistic documents. However, it is less effective when applied to historical documents, in languages other than English. In this study, we introduce an adaptation of PromptORE to extract relations from specialized documents, namely digital transcripts of trials from the Spanish Inquisition. Our approach involves fine-tuning transformer models with their pretraining objective on the data they will perform inference. We refer to this process as "biasing". Our Biased PromptORE addresses complex entity placements and genderism that occur in Spanish texts. We solve these issues by prompt engineering. We evaluate our method using Encoder-like models, corroborating our findings with experts' assessments. Additionally, we evaluate the performance using a binomial classification benchmark. Our results show a substantial improvement in accuracy -up to a 50% improvement with our Biased PromptORE models in comparison to the baseline models using standard PromptORE.