Extracting Novel Facts from Tables for Knowledge Graph Completion (Extended version)

June 28, 2019 Β· Declared Dead Β· πŸ› International Workshop on the Semantic Web

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Benno Kruit, Peter Boncz, Jacopo Urbani arXiv ID 1907.00083 Category cs.IR: Information Retrieval Cross-listed cs.DB Citations 25 Venue International Workshop on the Semantic Web Last Checked 4 months ago
Abstract
We propose a new end-to-end method for extending a Knowledge Graph (KG) from tables. Existing techniques tend to interpret tables by focusing on information that is already in the KG, and therefore tend to extract many redundant facts. Our method aims to find more novel facts. We introduce a new technique for table interpretation based on a scalable graphical model using entity similarities. Our method further disambiguates cell values using KG embeddings as additional ranking method. Other distinctive features are the lack of assumptions about the underlying KG and the enabling of a fine-grained tuning of the precision/recall trade-off of extracted facts. Our experiments show that our approach has a higher recall during the interpretation process than the state-of-the-art, and is more resistant against the bias observed in extracting mostly redundant facts since it produces more novel extractions.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Information Retrieval

Died the same way β€” πŸ‘» Ghosted