Computing semantic similarity of texts based on deep graph learning with ability to use semantic role label information

HIGHLIGHTS

• who: Majid Mohebbi from the DepartmentUniversity of have published the article: Computing semantic similarity of texts based on deep graph learning with ability to use semantic role label information, in the Journal: Scientific Reports Scientific Reports of 31/05/2022
• what: To be able to use the features of U-Net on the graph structure, the authors propose a g-U-Net based architecture. The authors evaluate the DGNN on STS2017 using Pearson and Spearman correlation coefficients.. The authors examine the efficiency of the DGNN with different layers over SRL + SDG, SRL + DG, and DG . . .
  

   

  

  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.