홈 › Papers

HyperText: Endowing FastText with Hyperbolic Geometry

2020-10-30 · Findings of the Association for Computational Linguistics 2020 · Yudong Zhu, Di Zhou, Jinghui Xiao, Xin Jiang, Xiao Chen, Qun Liu

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.

📄 PDF Abstract BibTeX arXiv:2010.16143

Code (3)

huawei-noah/Pretrained-Language-Model/tree/master/HyperText pytorch

jiean001/models_m/tree/main/hypertext mindspore

mindspore-ai/models/tree/master/research/nlp/hypertext mindspore

Tasks

Classification General Classification Text Classification

Methods 이 논문이 사용한 방법론

fastText fastText embeddings exploit subword information to construct word embeddings. Representations are learnt of character $n$-grams, and words represented as the sum of the…

Lorentzian Graph Convolutional Networks

2021-04-15 · Yiding Zhang, Xiao Wang, Chuan Shi, Nian Liu 외

Graph convolutional networks (GCNs) have received considerable research attention recently. Most GCNs learn the node representations in Euclidean geometry, but that could have a high distortion in the case of embedding g…

Hyperbolic Neural Networks

2018-05-23 · NeurIPS 2018 12 · Octavian-Eugen Ganea, Gary Bécigneul, Thomas Hofmann

Hyperbolic spaces have recently gained momentum in the context of machine learning due to their high capacity and tree-likeliness properties. However, the representational power of hyperbolic geometry is not yet on par w…

Graph Representation Learning Natural Language Inference Sentence Sentence Embeddings

Scalable Hyperbolic Recommender Systems

2019-02-22 · Benjamin Paul Chamberlain, Stephen R. Hardwick, David R. Wardrope, Fabon Dzogang 외

We present a large scale hyperbolic recommender system. We discuss why hyperbolic geometry is a more suitable underlying geometry for many recommendation systems and cover the fundamental milestones and insights that we …

Recommendation Systems

Brain-Inspired AI with Hyperbolic Geometry

2024-09-04 · Alexander Joseph, Nathan Francis, Meijke Balay

Artificial neural networks (ANNs) were inspired by the architecture and functions of the human brain and have revolutionised the field of artificial intelligence (AI). Inspired by studies on the latent geometry of the br…

Infrastructure-Agnostic Hypertext

2019-06-29 · Jakob Voß

This paper presents a novel and formal interpretation of the original vision of hypertext: infrastructure-agnostic hypertext is independent from specific standards such as data formats and network protocols. Its model is…