Network security field text data entity relationship extraction method based on multi-task learning
A multi-task learning and network security technology, applied in the field of text data entity relationship extraction, can solve the problems of heterogeneity and diversity, loose structure and organization, etc., and achieve the effect of broad application prospects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
example
[0117] Data set sentence: "The firewall can effectively resist the attack of hackers", which is processed by this method:
[0118] S1: First, the text sequence S={s 1 , s 2 …s n} Input into the secondary pre-trained language model ERNIE, encode it, and output the word vector sequence W={w 1 , w 2 …w n};
[0119] S2: Then, predict the relationship according to the word vector W output by ERNIE, and obtain the relationship set R, such as figure 2 shown;
[0120] S3: Splicing the two parts of R and W into X={x 1 , x 2 …x n}, and input it into Bi-GRU, use the forward and backward GRU to obtain the information hidden in the preceding and following texts, and the output sequence H={h 1 , h 2 …h n};
[0121] S4: Input sequence H={h 1 , h 2 …h n}, use two identical binary classifiers to extract the entity set E in the text, such as image 3 shown;
[0122] S5: Splicing the sequence H containing the hidden information and the entity set E, and then pairing according ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


