About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Gaetano Rossiello
- sl:arxiv_num : 2210.13952
- sl:arxiv_published : 2022-10-25T12:12:36Z
- sl:arxiv_summary : 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.@en
- sl:arxiv_title : KnowGL: Knowledge Generation and Linking from Text@en
- sl:arxiv_updated : 2022-11-10T01:29:17Z
- sl:bookmarkOf : https://arxiv.org/abs/2210.13952
- sl:creationDate : 2022-11-13
- sl:creationTime : 2022-11-13T10:48:17Z
Documents with similar tags (experimental)