文献类型: 外文期刊
作者: 李慧;;阎琰;;王烁;;刘娟;;崔运鹏
作者机构:
关键词: Text classification;Graph convolutional networks;Knowledge graph;Heterogeneous information network;Pre-trained model
期刊名称: NEURAL COMPUTING & APPLICATIONS
ISSN: 0941-0643
年卷期: 2023 年
页码:
收录情况: SCIE(2023版) ; ; EI(2023版)
摘要: Graph convolutional networks-based text classification methods have shown impressive success in further improving the classification results by considering the structural relationship between words and texts. However, existing GCN-based text classification methods tend to ignore the semantic representation of the node and the global structural information among nodes. Besides, only the word granularity information within the text, i.e., endogenous source, is used to represent the text. Furthermore, the existing graph convolutional network approaches are faced with major challenges to handle large and dense graphs, i.e., neighbor explosion and noisy inputs. To address these shortcomings, this paper proposes an inductive learning-based text classification method that utilizes representation learning on heterogeneous information networks and exogenous knowledge. Firstly, a weighted heterogeneous information network for text (HINT) is constructed by introducing exogenous knowledge, in which the node types cover text, entities and words. The unstructured text is represented as a structured heterogeneous information network, which expands the granularity of text features and makes full use of the exogenous structural information and explicit semantic information to enhance the interpretability of text information. Besides, we also enhanced the graph neural network against the challenges of neighbor explosion and noisy inputs derived from HINT using two strategies: graph sampling and Dropedge, for semi-supervised learning with improved classification performance. The effectiveness of our model is demonstrated by examining four publicly available text classification datasets. Based on experimental results, our approach achieves state-of-the-art performance on the text classification datasets.
分类号:
- 相关文献
作者其他论文 更多>>
-
Phosphorus application interferes expression of Fe uptake‑associated genes to feedback regulate Cd accumulation in rice (Oryza sativa L.) and relieves Cd toxicity via antioxidant defense
作者:Qina Huang;;Hua An;;Jiangmin Chen;;Xiaolin Li;;Guosheng Shao
关键词:
-
Single-cell RNA-seq of Lotus japonicus provide insights into identification and function of root cell types of legume
作者:孙占敏;;姜三杰;;王丹;;冉启凡;;胡丽珍;;熊军波;;唐益雄;;谷晓峰;;吴燕民;;梁哲
关键词:
-
The Importance of Salicylic Acid, Humic Acid and Fulvic Acid on Crop Production
作者:M. Hesam Shahrajabian;;Wenli Sun
关键词:
-
Gut microbiome in tumorigenesis and therapy of colorectal cancer
作者:Ling Wang;; Ke‐Chun Yu;;Yun‐qing Hou;;Min Guo;; Fan Yao;; Zhen‐Xia Chen
关键词:biomarkers; CRC; gut microbiome; probiotics; tumorigenesis
-
Highly efficient Agrobacterium rhizogenes-mediated hairy root transformation for gene editing analysis in cotton
作者:Lili Zhou;;Yali Wang;;Peilin Wang;;Chunling Wang;;Jiamin Wang;;Xingfen Wang;;Hongmei Cheng
关键词:
-
Assessment of Wine Quality, Traceability and Detection of Grapes Wine, Detection of Harmful Substances in Alcohol and Liquor Composition Analysis
作者:M. Hesam Shahrajabian;;Wenli Sun
关键词:
-
CRISPR/Cas9-Mediated Mutagenesis of GmFAD2-1A and/or GmFAD2-1B to Create High-Oleic-Acid Soybean
作者:Mingxue Fu;; Li Chen;; Yupeng Cai;; Qiang Su;; Yingying Chen;; Wensheng Hou
关键词: