World Wide Web

Pure mathematics

Hyperbolic space

Semantic space

Materials science

Theoretical computer science

Range (aeronautics)

Classifier (UML)

Economics

Market economy

Computer science

WordNet

Hypertext

Natural language processing

Hierarchy

Pattern recognition (psychology)

Mathematics

Artificial intelligence

Geometry

Composite material

Euclidean space

Euclidean geometry

Natural language data exhibit tree-like hierarchical structures such as the hypernym-hyponym hierarchy in WordNet. FastText, as the state-of-the-art text classifier based on shallow neural network in Euclidean space, may not represent such hierarchies precisely with limited representation capacity. Considering that hyperbolic space is naturally suitable for modelling tree-like hierarchical data, we propose a new model named HyperText for efficient text classification by endowing FastText with hyperbolic geometry. Empirically, we show that HyperText outperforms FastText on a range of text classification tasks with much reduced parameters.

HyperText: Endowing FastText with Hyperbolic Geometry