A Study on the Interrelationship with SLM-based Knowledge Graph
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This paper explores the integration of Small Language Models (SLMs) with knowledge graphs (KGs) to enhance interoperability and knowledge representation. While Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding, their computational demands and lack of domain-specific focus present challenges. SLMs, with their smaller footprint and lower resource requirements, offer a promising alternative, particularly for creating and managing specialized knowledge graphs. We propose a novel framework that leverages SLMs to extract entities and relations from unstructured text, which are then used to construct and enrich a knowledge graph. This approach focuses on improving the interoperability between different knowledge sources by creating a unified, machine-readable representation.
Abstract
This paper explores the integration of Small Language Models (SLMs) with knowledge graphs (KGs) to enhance interoperability and knowledge representation. While Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding, their computational demands and lack of domain-specific focus present challenges. SLMs, with their smaller footprint and lower resource requirements, offer a promising alternative, particularly for creating and managing specialized knowledge graphs. We propose a novel framework that leverages SLMs to extract entities and relations from unstructured text, which are then used to construct and enrich a knowledge graph. This approach focuses on improving the interoperability between different knowledge sources by creating a unified, machine-readable representation.