ShihanYang/UKGEbert
Uncertain Knowledge Graphs Embedding with BERT Pretrained Language Model
This project helps researchers and data scientists working with knowledge graphs where the relationships between entities are not always certain. It takes a knowledge graph with entities, relations, and associated confidence scores as input. Using a BERT model, it helps in predicting missing links or refining existing relationships within the graph, outputting more accurate and contextually rich graph embeddings. This is ideal for those who need to extract more nuanced insights from complex, uncertain relational data.
No commits in the last 6 months.
Use this if you are working with knowledge graphs containing uncertain or probabilistic relationships and need to improve the accuracy of link prediction or entity-relation embeddings.
Not ideal if your knowledge graph data is completely certain and you do not require handling of probabilistic relationships, or if you need to build knowledge graphs from unstructured text rather than refine existing ones.
Stars
17
Forks
2
Language
Python
License
—
Category
Last pushed
Oct 10, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/ShihanYang/UKGEbert"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.