KGGen: Text To Knowledge Graph

Belinda Mo, Kyssen Yu, Joshua Kazdan, Proud Mpala, Lisa Yu, Chris Cundy, Charilaos Kanatsoulis, Sanmi Koyejo

Keywords: text to knowledge graph, synthetic data for GNN, GNN, KG, knowledge graph

Abstract: Recent interest in building foundation models for KGs has highlighted a fundamental challenge: knowledge-graph data is relatively scarce. The best-known KGs are primarily human-labeled, created by pattern-matching, or extracted using early NLP techniques. While human-generated KGs are in short supply, automatically extracted KGs are of questionable quality. We present a solution to this data scarcity problem in the form of a text-to-KG generator (KGGen), a package that uses language models to create high-quality graphs from plaintext. Unlike other KG extractors, KGGen clusters related entities to reduce sparsity in extracted KGs. KGGen is available as a Python package (pip install NAME REDACTED), making it accessible to anyone with an OpenAI API key. Along with KGGen, we release the first benchmark that tests an extractor's ability to produce a useful KG from plain text. We benchmark our new tool against existing extractors and demonstrate far superior performance.

Submission Number: 34