A Recommendation Method for Technical Writing Based on Self-Attention Mechanism
A recommendation method and attention technology, applied in the field of social media, can solve problems such as spending a lot of time, and achieve the effect of high recall rate and high normalized loss cumulative gain
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0065] This embodiment describes the process used in the collection of data sets in the present invention, the structure and detailed parameters of the deep technical writing recommendation model involved, and the experimental results.
[0066] The invention is a method for recommending scientific writing based on a self-attention mechanism, and the invention can be applied to scientific paper websites such as arxiv, DBLP, IEEE, ACM, and Springer. During specific implementation, the method crawls data from scientific and technical paper websites, such as arxiv, as an experimental data set, respectively according to figure 1 The order of the data collection phase, candidate set screening, training phase, real recommendation list acquisition and testing phase, the following process is performed:
[0067] In the data collection stage, first of all, the website arxiv of scientific papers is used as the practice object, and the process of collecting data is as follows:
[0068] St...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


