Abstract
Knowledge graphs, which provide numerous facts in a machine-friendly format, are incomplete. Information that we induce from such graphs – e.g. entity embeddings, relation representations or patterns – will be affected by the imbalance in the information captured in the graph – by biasing representations, or causing us to miss potential patterns. To partially compensate for this situation we describe a method for representing knowledge graphs that capture an intensional representation of the original extensional information. This representation is very compact, and it abstracts away from individual links, allowing us to find better path candidates, as shown by the results of link prediction using this information.- Anthology ID:
- S19-1016
- Volume:
- Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Venues:
- SemEval | *SEM
- SIGs:
- SIGLEX | SIGSEM
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 147–157
- Language:
- URL:
- https://aclanthology.org/S19-1016
- DOI:
- 10.18653/v1/S19-1016
- Cite (ACL):
- Vivi Nastase and Bhushan Kotnis. 2019. Abstract Graphs and Abstract Paths for Knowledge Graph Completion. In Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019), pages 147–157, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Abstract Graphs and Abstract Paths for Knowledge Graph Completion (Nastase & Kotnis, SemEval-*SEM 2019)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/S19-1016.pdf
- Data
- NELL