Heterogeneous graph neural network for short text classification

HIGHLIGHTS

• who: Bingjie Zhang and collaborators from the College of Big Data and Information Engineering, Guizhou University, Guiyang, China have published the research: Heterogeneous Graph Neural Network for Short Text Classification, in the Journal: (JOURNAL)
• what: The authors propose a heterogeneous graph convolutional network suitable for short texts. The authors propose a heterogeneous graph around text, words, and POS tags, using a multilayer GCN to learn the features of the three graphs separately, and combine the information of different graphs to learn short texts. In this paper, ablation experiments of small images and various heterogeneous Text . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.