PE: A Poincare Explanation Method for Fast Text Hierarchy Generation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Qian, Li, Dongyang, He, Xiaofeng, Li, Hongzhao, Yi, Hongyu
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910482615500800
author Chen, Qian
Li, Dongyang
He, Xiaofeng
Li, Hongzhao
Yi, Hongyu
author_facet Chen, Qian
Li, Dongyang
He, Xiaofeng
Li, Hongzhao
Yi, Hongyu
contents The black-box nature of deep learning models in NLP hinders their widespread application. The research focus has shifted to Hierarchical Attribution (HA) for its ability to model feature interactions. Recent works model non-contiguous combinations with a time-costly greedy search in Eculidean spaces, neglecting underlying linguistic information in feature representations. In this work, we introduce a novel method, namely Poincare Explanation (PE), for modeling feature interactions with hyperbolic spaces in a time efficient manner. Specifically, we take building text hierarchies as finding spanning trees in hyperbolic spaces. First we project the embeddings into hyperbolic spaces to elicit inherit semantic and syntax hierarchical structures. Then we propose a simple yet effective strategy to calculate Shapley score. Finally we build the the hierarchy with proving the constructing process in the projected space could be viewed as building a minimum spanning tree and introduce a time efficient building algorithm. Experimental results demonstrate the effectiveness of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2403_16554
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PE: A Poincare Explanation Method for Fast Text Hierarchy Generation
Chen, Qian
Li, Dongyang
He, Xiaofeng
Li, Hongzhao
Yi, Hongyu
Computation and Language
Artificial Intelligence
The black-box nature of deep learning models in NLP hinders their widespread application. The research focus has shifted to Hierarchical Attribution (HA) for its ability to model feature interactions. Recent works model non-contiguous combinations with a time-costly greedy search in Eculidean spaces, neglecting underlying linguistic information in feature representations. In this work, we introduce a novel method, namely Poincare Explanation (PE), for modeling feature interactions with hyperbolic spaces in a time efficient manner. Specifically, we take building text hierarchies as finding spanning trees in hyperbolic spaces. First we project the embeddings into hyperbolic spaces to elicit inherit semantic and syntax hierarchical structures. Then we propose a simple yet effective strategy to calculate Shapley score. Finally we build the the hierarchy with proving the constructing process in the projected space could be viewed as building a minimum spanning tree and introduce a time efficient building algorithm. Experimental results demonstrate the effectiveness of our approach.
title PE: A Poincare Explanation Method for Fast Text Hierarchy Generation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2403.16554