Recently, hyperbolic deep neural networks (HDNNs) have been gaining momentum as the
deep representations in the hyperbolic space provide high fidelity embeddings with few …

For image segmentation, the current standard is to perform pixel-level optimization and
inference in Euclidean output embedding spaces through linear hyperplanes. In this work …

Capturing associations for knowledge graphs (KGs) through entity alignment, entity type
inference and other related tasks benefits NLP applications with comprehensive knowledge …

Taxonomies consist of machine-interpretable semantics and provide valuable knowledge for
many web applications. For example, online retailers (eg, Amazon and eBay) use …

Automatic construction of a taxonomy supports many applications in e-commerce, web
search, and question answering. Existing taxonomy expansion or completion methods …

Hyperbolic space has become a popular choice of manifold for representation learning of
various datatypes from tree-like structures and text to graphs. Building on the success of …

Taxonomies are important knowledge ontologies that underpin numerous applications on a
daily basis, but many taxonomies used in practice suffer from the low coverage issue. We …

Automatically constructing taxonomy finds many applications in e-commerce and web
search. One critical challenge is as data and business scope grow in real applications, new …

Taxonomies, which organize knowledge hierarchically, support various practical web
applications such as product navigation in online shopping and user profile tagging on …

Taxonomies are valuable resources for many applications, but the limited coverage due to
the expensive manual curation process hinders their general applicability. Prior works …