KRR-Oxford/HierarchyTransformers
Language Models as Hierarchy Encoders
This helps researchers and knowledge managers understand how concepts relate to each other in complex hierarchies, like those found in ontologies or taxonomies. You provide a list of entity names, and it outputs numerical representations (embeddings) that reflect their hierarchical positions. This is for knowledge engineers, ontology developers, and data scientists who need to capture hierarchical relationships using language models.
Use this if you need to embed text-based concepts into a hierarchical structure to predict relationships like 'is-a' or 'part-of'.
Not ideal if your data doesn't have a clear hierarchical structure or if you only need simple text similarity without hierarchical context.
Stars
40
Forks
8
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 06, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/KRR-Oxford/HierarchyTransformers"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lucidrains/x-transformers
A concise but complete full-attention transformer with a set of promising experimental features...
kanishkamisra/minicons
Utility for behavioral and representational analyses of Language Models
lucidrains/simple-hierarchical-transformer
Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
lucidrains/dreamer4
Implementation of Danijar's latest iteration for his Dreamer line of work
Nicolepcx/Transformers-in-Action
This is the corresponding code for the book Transformers in Action