KnowGL: Knowledge Generation and Linking from Text
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.
Cite
Text
Rossiello et al. "KnowGL: Knowledge Generation and Linking from Text." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.27084Markdown
[Rossiello et al. "KnowGL: Knowledge Generation and Linking from Text." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/rossiello2023aaai-knowgl/) doi:10.1609/AAAI.V37I13.27084BibTeX
@inproceedings{rossiello2023aaai-knowgl,
title = {{KnowGL: Knowledge Generation and Linking from Text}},
author = {Rossiello, Gaetano and Chowdhury, Md. Faisal Mahbub and Mihindukulasooriya, Nandana and Cornec, Owen and Gliozzo, Alfio Massimiliano},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2023},
pages = {16476-16478},
doi = {10.1609/AAAI.V37I13.27084},
url = {https://mlanthology.org/aaai/2023/rossiello2023aaai-knowgl/}
}