# Fine-Grained Entity Typing in Hyperbolic Space

arXiv: https://arxiv.org/abs/1906.02505 · HTML: https://mlsanity.com/paper/1906.02505/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2019.

## Built on by (most cited first, 9 of 9)

- [Fully Hyperbolic Neural Networks](https://mlsanity.com/paper/2105.14686/) (2021)
- [The Numerical Stability of Hyperbolic Representation Learning](https://mlsanity.com/paper/2211.00181/) (2022)
- [Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach](https://mlsanity.com/paper/2106.04941/) (2021)
- [Comparing Euclidean and Hyperbolic Embeddings on the WordNet Nouns Hypernymy Graph](https://mlsanity.com/paper/2109.07488/) (2021)
- [Augmenting the User-Item Graph with Textual Similarity Models](https://mlsanity.com/paper/2109.09358/) (2021)
- [Hyperbolic Disentangled Representation for Fine-Grained Aspect Extraction](https://mlsanity.com/paper/2112.09215/) (2021)
- [Normed Spaces for Graph Embedding](https://mlsanity.com/paper/2312.01502/) (2023)
- [FGNET-RH: Fine-Grained Named Entity Typing via Refinement in Hyperbolic Space](https://mlsanity.com/paper/2101.11212/) (2021)
- [sHGCN: Simplified hyperbolic graph convolutional neural networks](https://mlsanity.com/paper/2506.14438/) (2025)

## Abstract (arXiv)

How can we represent hierarchical information present in large type inventories for entity typing? We study the ability of hyperbolic embeddings to capture hierarchical relations between mentions in context and their target types in a shared vector space. We evaluate on two datasets and investigate two different techniques for creating a large hierarchical entity type inventory: from an expert-generated ontology and by automatically mining type co-occurrences. We find that the hyperbolic model yields improvements over its Euclidean counterpart in some, but not all cases. Our analysis suggests that the adequacy of this geometry depends on the granularity of the type inventory and the way hierarchical relations are inferred.