Modeling Fine-Grained Entity Types with Box Embeddings

Yasumasa Onoe
Yasumasa Onoe
Michael Boratko
Michael Boratko
Cited by: 0|Bibtex|Views1
Other Links: arxiv.org

Abstract:

Neural entity typing models typically represent entity types as vectors in a high-dimensional space, but such spaces are not well-suited to modeling these types' complex interdependencies. We study the ability of box embeddings, which represent entity types as d-dimensional hyperrectangles, to represent hierarchies of fine-grained entit...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments