English

KnowGL: Knowledge Generation and Linking from Text

Computation and Language 2022-11-23 v5 Artificial Intelligence Information Retrieval

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.

Keywords

Cite

@article{arxiv.2210.13952,
  title  = {KnowGL: Knowledge Generation and Linking from Text},
  author = {Gaetano Rossiello and Md Faisal Mahbub Chowdhury and Nandana Mihindukulasooriya and Owen Cornec and Alfio Massimiliano Gliozzo},
  journal= {arXiv preprint arXiv:2210.13952},
  year   = {2022}
}

Comments

AAAI-23 Demo Track

R2 v1 2026-06-28T04:27:27.933Z