AutoOntic builds organized knowledge graphs automatically from text
AutoOntic: Automatic Ontology Induction from Text for Knowledge Graph Construction
Computation and LanguageArtificial IntelligenceMachine Learning
Summary
Building good knowledge graphs from text usually requires organizing the types of things and their relationships carefully. Existing tools often create simple, flat groupings without clear categories or rules. The authors developed AutoOntic, a system that reads text and automatically builds a structured hierarchy of types and their relations, making the knowledge graph more organized. Their method checks which types relate to each other using language models, improving accuracy. Tests show AutoOntic creates types closely matching known classifications and helps knowledge graphs retrieve information more accurately.
What this means in practice
- •For knowledge graph engineers: Automatically generate structured ontologies from text to improve the organization and retrieval in knowledge graph construction workflows.
- •For enterprise search developers: Enhance search accuracy by employing automatically induced ontologies to better categorize entities and relations in retrieval-augmented generation systems.
Authors
Alla Chepurova, Aydar Bulatov, Mikhail Burtsev, Yuri Kuratov
Abstract
Graph-based retrieval-augmented generation depends on the quality of the knowledge graph (KG) it retrieves over, yet schema-free LLM-based extraction pipelines typically produce flat graphs: deduplicated entities and relations with no type hierarchy and no domain/range constraints. We present AutoOntic, a pipeline that automatically constructs an ontology from text by canonicalizing open-vocabulary entity types and relations, inducing a hierarchy over the canonicalized types, and mining relation-level domain and range constraints. Its hierarchy induction procedure prioritizes types using corpus-derived relation-argument profiles and places them through local, LLM-adjudicated parent/child checks, allowing newly inserted types to trigger reassignment of existing parent-child links. The resulting hierarchy constrains entity deduplication and supports the induction of relation-level domain/range constraints. For intrinsic evaluation, we introduce a reference-based protocol that classifies induced ontology types as exact, broader, narrower, or unrelated to reference domain and range classes. On the Wikidata-TekGen and DBpedia-WebNLG subsets of Text2KGBench, over 90% of AutoOntic's induced endpoint types are semantically aligned with the reference classes across two LLM backbones: about half match exactly, while most remaining differences concern granularity. On MINE, knowledge graphs organized using an ontology built by AutoOntic achieve 88% retrieval accuracy. AutoOntic is available at https://github.com/screemix/AutoOntic.