HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning

09/22/2021
by   Mingyu Derek Ma, et al.
0

Taxonomies are valuable resources for many applications, but the limited coverage due to the expensive manual curation process hinders their general applicability. Prior works attempt to automatically expand existing taxonomies to improve their coverage by learning concept embeddings in Euclidean space, while taxonomies, inherently hierarchical, more naturally align with the geometric properties of a hyperbolic space. In this paper, we present HyperExpan, a taxonomy expansion algorithm that seeks to preserve the structure of a taxonomy in a more expressive hyperbolic embedding space and learn to represent concepts and their relations with a Hyperbolic Graph Neural Network (HGNN). Specifically, HyperExpan leverages position embeddings to exploit the structure of the existing taxonomies, and characterizes the concept profile information to support the inference on unseen concepts during training. Experiments show that our proposed HyperExpan outperforms baseline models with representation learning in a Euclidean feature space and achieves state-of-the-art performance on the taxonomy expansion benchmarks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/16/2022

HyperMiner: Topic Taxonomy Mining with Hyperbolic Embedding

Embedded topic models are able to learn interpretable topics even with l...
research
10/04/2022

Bringing robotics taxonomies to continuous domains via GPLVM on hyperbolic manifolds

Robotic taxonomies have appeared as high-level hierarchical abstractions...
research
05/28/2020

Hyperbolic Manifold Regression

Geometric representation learning has recently shown great promise in se...
research
05/18/2023

Taxonomy Completion with Probabilistic Scorer via Box Embedding

Taxonomy completion, a task aimed at automatically enriching an existing...
research
06/05/2021

Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations

Automatic construction of a taxonomy supports many applications in e-com...
research
02/22/2023

DNG: Taxonomy Expansion by Exploring the Intrinsic Directed Structure on Non-Gaussian Space

Taxonomy expansion is the process of incorporating a large number of add...
research
01/27/2021

Enquire One's Parent and Child Before Decision: Fully Exploit Hierarchical Structure for Self-Supervised Taxonomy Expansion

Taxonomy is a hierarchically structured knowledge graph that plays a cru...

Please sign up or login with your details

Forgot password? Click here to reset