KnowGL: Knowledge Generation and Linking from Text

TL;DR

KnowGL is a tool that converts text into structured knowledge graph data using fine-tuned sequence-to-sequence models, enabling semantic annotation and easy navigation of extracted facts.

Contribution

We introduce KnowGL, a novel approach that leverages pre-trained language models to generate structured KG assertions from text, with a user-friendly web interface.

Findings

Effective conversion of text into KG assertions

Supports entity recognition, typing, and relation extraction

Accessible via a web application

Abstract

We propose KnowGL, a tool that allows converting text into structured relational data represented as a set of ABox assertions compliant with the TBox of a given Knowledge Graph (KG), such as Wikidata. We address this problem as a sequence generation task by leveraging pre-trained sequence-to-sequence language models, e.g. BART. Given a sentence, we fine-tune such models to detect pairs of entity mentions and jointly generate a set of facts consisting of the full set of semantic annotations for a KG, such as entity labels, entity types, and their relationships. To showcase the capabilities of our tool, we build a web application consisting of a set of UI widgets that help users to navigate through the semantic data extracted from a given input text. We make the KnowGL model available at https://huggingface.co/ibm/knowgl-large.