Concetti Chiave
PE introduces a novel method using hyperbolic spaces to model feature interactions efficiently, demonstrating effectiveness in generating hierarchical explanations.
Statistiche
Inspired by Poincaré model, we propose a framework to project the embeddings into hyperbolic spaces, which exhibit better inductive biases for syntax and semantic hierarchical structures.
We evaluate the proposed method on three classification datasets with BERT, and the results demonstrate effectiveness.
Our code is available at https://github.com/qq31415926/PE.