☆ 4.5 Article

Text classification based on PEGCN: Graph convolution classification using location information and edge features

EXPERT SYSTEMS (2023)

Related references

Note: Only part of the references are listed.

Proceedings Paper Computer Science, Artificial Intelligence

Label Incorporated Graph Neural Networks for Text Classification

Yuan Xin et al.

Summary: This research considers incorporating label information while building the graph by adding text-label-text paths, through which supervision information can propagate more directly in the graph. By treating labels as nodes in the graph and connecting them with text nodes, label embeddings are jointly learned with text embeddings, resulting in more accurate text embeddings for improved downstream text classification tasks. Extensive results on benchmark datasets show significant performance improvements over baseline methods.

2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications