KnowGL: Knowledge Generation and Linking from Text

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.

Authors

• Gaetano Rossiello IBM Research AI
• Md. Faisal Mahbub Chowdhury IBM Research AI
• Nandana Mihindukulasooriya IBM Research AI
• Owen Cornec IBM Research AI
• Alfio Massimiliano Gliozzo IBM Research AI

Keywords

• Information Extraction
• Knowledge Representation
• Machine Learning
• Natural Language Processing