Zero-Shot Open-Schema Entity Structure Discovery

TL;DR

This paper presents ZOES, a zero-shot method for extracting entity structures from text without relying on predefined schemas or annotations, improving completeness and generalizability across domains.

Contribution

Introduces ZOES, a novel zero-shot approach that enhances LLM-based entity structure extraction through a principled enrichment, refinement, and unification mechanism without requiring schemas or annotations.

Findings

ZOES improves entity structure extraction across multiple domains.

The method enhances the completeness of extracted structures.

It demonstrates strong generalizability and effectiveness.

Abstract

Entity structure extraction, which aims to extract entities and their associated attribute-value structures from text, is an essential task for text understanding and knowledge graph construction. Existing methods based on large language models (LLMs) typically rely heavily on predefined entity attribute schemas or annotated datasets, often leading to incomplete extraction results. To address these challenges, we introduce Zero-Shot Open-schema Entity Structure Discovery (ZOES), a novel approach to entity structure extraction that does not require any schema or annotated samples. ZOES operates via a principled mechanism of enrichment, refinement, and unification, based on the insight that an entity and its associated structure are mutually reinforcing. Experiments demonstrate that ZOES consistently enhances LLMs' ability to extract more complete entity structures across three different domains, showcasing both the effectiveness and generalizability of the method. These findings suggest that such an enrichment, refinement, and unification mechanism may serve as a principled approach to improving the quality of LLM-based entity structure discovery in various scenarios.