Creating a Fine Grained Entity Type Taxonomy Using LLMs

TL;DR

This paper demonstrates how GPT-4 and GPT-4 Turbo can autonomously generate a detailed, extensive entity type taxonomy with over 5000 types, improving information extraction tasks.

Contribution

It introduces a novel iterative prompting method for large language models to create fine-grained entity taxonomies automatically.

Findings

Generated taxonomy contains over 5000 nuanced entity types.

The taxonomy significantly improves relation and event argument extraction.

The approach is effective and adaptable for expanding entity classifications.

Abstract

In this study, we investigate the potential of GPT-4 and its advanced iteration, GPT-4 Turbo, in autonomously developing a detailed entity type taxonomy. Our objective is to construct a comprehensive taxonomy, starting from a broad classification of entity types - including objects, time, locations, organizations, events, actions, and subjects - similar to existing manually curated taxonomies. This classification is then progressively refined through iterative prompting techniques, leveraging GPT-4's internal knowledge base. The result is an extensive taxonomy comprising over 5000 nuanced entity types, which demonstrates remarkable quality upon subjective evaluation. We employed a straightforward yet effective prompting strategy, enabling the taxonomy to be dynamically expanded. The practical applications of this detailed taxonomy are diverse and significant. It facilitates the creation of new, more intricate branches through pattern-based combinations and notably enhances information extraction tasks, such as relation extraction and event argument extraction. Our methodology not only introduces an innovative approach to taxonomy creation but also opens new avenues for applying such taxonomies in various computational linguistics and AI-related fields.