Deep learning--based models have surpassed classical machine learning--based
approaches in various text classification tasks, including sentiment analysis, news …

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

Graph convolutional neural networks (GCNs) embed nodes in a graph into Euclidean space,
which has been shown to incur a large distortion when embedding real-world graphs with …

Ranking models lie at the heart of research on information retrieval (IR). During the past
decades, different techniques have been proposed for constructing ranking models, from …

Hyperbolic embeddings offer excellent quality with few dimensions when embedding
hierarchical data structures. We give a combinatorial construction that embeds trees into …

The quality of the representations achieved by embeddings is determined by how well the
geometry of the embedding space matches the structure of the data. Euclidean space has …

We introduce hyperbolic attention networks to endow neural networks with enough capacity
to match the complexity of data with hierarchical and power-law structure. A few recent …

Hyperbolic neural networks have shown great potential for modeling complex data.
However, existing hyperbolic networks are not completely hyperbolic, as they encode …

Question answering, serving as one of important tasks in natural language processing,
enables machines to understand questions in natural language and answer the questions …

Abstract The International Classification of Diseases (ICD) provides a standardized way for
classifying diseases, which endows each disease with a unique code. ICD coding aims to …