.png){kind=icon}
返回
Hierarchical Multi-Granularity Interaction Graph Convolutional Network for Long Document Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/TASLP.2024.3369530.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
With the growing demand for text analytics, long document classification (LDC) has received extensive attention, and great progress has been made. To reveal the complex structure and extract the intrinsic feature, the current approaches focus on modeling a long sequence with sparse attention or representing word-sentence or word-section relations partially. However, the thorough hierarchical structure from words, sentences to sections of long documents remains relatively unexplored. For this purpose, we propose a novel Hierarchical Multi-granularity Interaction Graph Convolutional Network (HMIGCN) for long document classification, in which three different granularity graphs, i.e., section graph, sentence graph and word graph, are constructed hierarchically. The section graph encapsulates the macrostructure of a long document, while the sentence and word graphs delve into the document's microstructure. Notably, within the sentence graph, we introduce a Global-Local Graph Convolutional (GLGC) block to adaptively capture both global and local dependency structures among sentence nodes. Additionally, to integrate the three graph networks as a whole, two well-designed techniques, namely section-guided pooling block and transfer fusion block, are proposed to train the model jointly by promoting each other. Extensive experiments on five long document datasets show that our model outperforms the existing state-of-the-art LDC models.
Keyword:
Transformers
Computational modeling
Convolutional neural networks
Adaptation models
Speech processing
Task analysis
Context modeling
Long document classification
hierarchical multi-granularity interaction graph convolutional network
hierarchical graph pooling
global-local graph convolution
期刊
I
IF:
5.1
论文数:
2.6K
被引数:
1.1W
机构
引用论文
Disturbed vegetation reconstruction using the biomization method from Japanese pollen data: Modern and Late Quaternary samples基于日本花粉数据的生物化方法对受损植被的重建：现代与晚更新世样品
.png){kind=icon}
PREAI
分享收藏分享收藏
Chemical Properties and Therapeutic Potential of Citral, a Monoterpene Isolated from Lemongrass
PREAI
分享收藏Definitive evidence that a single N-glycan among three glycans on inducible costimulator is required for proper protein trafficking and ligand binding明确的证据表明，在可诱导的共刺激物上的三个聚糖中，单个N-聚糖对于适当的蛋白质运输和配体结合是必需的
PREAI
分享收藏
查看更多内容