Hierarchical Graph Convolutional Networks for Structured Long Document Classification

doi:10.1109/TNNLS.2022.3185295

Hierarchical Graph Convolutional Networks for Structured Long Document Classification

2023-10-01

9

PRE

AI

DOI：10.1109/TNNLS.2022.3185295

Original

Original request for help

Save

Abstract

En 中文

Long document classification (LDC) has been a focused interest in natural language processing (NLP) recently with the exponential increase of publications. Based on the pretrained language models, many LDC methods have been proposed and achieved considerable progression. However, most of the existing methods model long documents as sequences of text while omitting the document structure, thus limiting the capability of effectively representing long texts carrying structure information. To mitigate such limitation, we propose a novel hierarchical graph convolutional network (HGCN) for structured LDC in this article, in which a section graph network is proposed to model the macrostructure of a document and a word graph network with a decoupled graph convolutional block is designed to extract the fine-grained features of a document. In addition, an interaction strategy is proposed to integrate these two networks as a whole by propagating features between them. To verify the effectiveness of the proposed model, four structured long document datasets are constructed, and the extensive experiments conducted on these datasets and another unstructured dataset show that the proposed method outperforms the state-of-the-art related classification methods.

Keywords:

Transformers

Context modeling

Computational modeling

Complexity theory

Task analysis

Analytical models

Feature extraction

Decoupled graph convolution

document and text processing

graph pooling

hierarchical graph convolutional networks (HGCNs)

long document classification (LDC)

Hierarchical Graph Convolutional Networks for Structured Long Document Classification

Abstract

Journal

Organization