KnowGL: Knowledge Generation and Linking from Text
This addresses the problem of automating knowledge extraction from text for users needing structured data, but it is incremental as it builds on existing sequence-to-sequence models.
The authors tackled the problem of converting text into structured relational data compliant with a Knowledge Graph like Wikidata, and they developed KnowGL, a tool that uses fine-tuned pre-trained language models to generate entity labels, types, and relationships from sentences, with a web application for navigation.
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.