Creating a Fine Grained Entity Type Taxonomy Using LLMs
This work addresses the need for fine-grained entity taxonomies in computational linguistics and AI, offering a novel automated approach that enhances tasks like relation extraction, though it is incremental in building upon existing manual taxonomies.
The study tackled the problem of creating a detailed entity type taxonomy by using GPT-4 and GPT-4 Turbo to autonomously develop a comprehensive taxonomy with over 5000 nuanced entity types, demonstrating high quality in subjective evaluation.
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.