HyperText: Endowing FastText with Hyperbolic Geometry
arXiv:2010.16143
Abstract
Natural language data exhibit tree-like hierarchical structures such as the hypernym-hyponym relations in WordNet. FastText, as the state-of-the-art text classifier based on shallow neural network in Euclidean space, may not model such hierarchies precisely with limited representation capacity. Considering that hyperbolic space is naturally suitable for modeling 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.
arXiv commentFindings of EMNLP 2020
References in corpus (8)
- Hyperbolic Geometry of Complex Networks
- Poincaré GloVe: Hyperbolic Word Embeddings
- Riemannian Adaptive Optimization Methods
- PKUSEG: A Toolkit for Multi-Domain Chinese Word Segmentation
- CLUE: A Chinese Language Understanding Evaluation Benchmark
- Hyperbolic Attention Networks
- Scalable Hyperbolic Recommender Systems
- HyperKG: Hyperbolic Knowledge Graph Embeddings for Knowledge Base Completion