BiGRU judgment result tendency analysis method based on attention mechanism
A technology of judgment results and analysis methods, applied in the fields of deep learning and natural language processing, can solve problems such as information loss and classification accuracy reduction, and achieve the effects of reducing loss, improving accuracy, and personalization scalability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0078] Judgment text: The plaintiff Qin Moujia and the defendant Cao Mou were allowed to divorce;
[0079] Judgment sequence: (Permit, Plaintiff, Qin Jia, and, Defendant, Cao, Divorce).
[0080] Word vector matrix: (w 1 ,w 2 ,w 3 ,",w n )→S=(s 1 ,s 2 ,s 3 ,",s n ).
[0081] Step 7: Feature vector of word vector: Input the word vector into the BiGRU network for calculation to obtain the feature vector. Such as figure 2 As shown, the word vector sequence S=(s 1 ,s 2 ,...,S n-1 ,s n ) Enter the BiGRU network, which is x in the formula t After the calculation of each unit of the network layer, the feature vector corresponding to the word vector is finally obtained.
[0082] z t =σ(W z ·[H t-1 ,x t ])
[0083] r t =σ(W r ·[H t-1 ,x t ])
[0084]
[0085]
[0086] The specific description is: x t Is the input data, h t Is the output of the current GRU calculation unit, h t-1 Is the calculation output of the previous calculation unit, z t Is the update gate, r t Is the reset gate, z t And r ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 



