Abstract graphs and abstract paths for knowledge graph completion
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 representa...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Chapter/Article Conference Paper |
| Language: | English |
| Published: |
June 2019
|
| In: |
Lexical and Computational Semantics (*SEM) - proceedings of the eighth conference
Year: 2019, Pages: 147-157 |
| Online Access: | Verlag, Volltext: https://www.aclweb.org/anthology/S19-1016
|
| Author Notes: | Vivi Nastase, Bhushan Kotnis |
| Summary: | 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. |
|---|---|
| Item Description: | Gesehen am 16.07.2019 |
| Physical Description: | Online Resource |
| ISBN: | 9781948087933 |