.png){kind=icon}
返回
A Heterogeneous Directed Graph Attention Network for inductive text classification using multilevel semantic embeddings
.png){kind=icon}
OA
AI
DOI：10.1016/j.knosys.2024.111797.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In the current study, a novel network model is proposed for text classification based on Graph Attention Networks (GATs) and sentence -transformer embeddings. Most existing methods with a pretraining model as an input layer still treat words as the minimum processing unit. However, word embedding is not an efficient and appropriate solution when dealing with long texts containing many professional words. This study aims to design a model capable of handling text classification tasks at multilevel semantic segmentation. The main contribution of this study is that a novel GAT variant is designed using global nodes and Squeeze -and -Excitation Networks (SENet) to capture semantic information. Moreover, a novel unidirectional attention mechanism is introduced for our model to avoid the message passing of irrelevant noisy information within global nodes. The numerical results show that according to the characteristics of datasets, specific semantic information combinations can effectively improve the accuracy and performance of text classification. Without fine-tuning of the pretrained encoder, the new state-of-the-art performance is achieved on three benchmark datasets. In addition, a comprehensive analysis of the graph attention mechanism in the model for specific cases suggests that the unidirectional attention mechanism and the use of global nodes are key contributing factors to multilevel semantic fusion.
Keyword:
Text classification
Multilevel semantics
Graph Neural Networks
Graph Attention Networks
Text segmentation
Sentence-transformer
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Damage detection in slab structures based on two-dimensional curvature mode shape method and Faster R-CNN基于二维曲率模态法和Faster r-cnn的板结构损伤检测OAAI
OAAI分享收藏Joint Learning With BERT-GCN and Multi-Attention for Event Text Classification and Event Assignment.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏Quantum probability-inspired graph neural network for document representation and classificationNEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
查看更多内容