Named entity extraction method and device and medium
A named entity, named entity recognition technology, applied in special data processing applications, instruments, electrical digital data processing and other directions, can solve problems such as confusing subdivision types, and achieve the effect of low overall cost
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0042] Using the recognition model to extract subdivided named entities not only has poor accuracy, but also has the problems of high training cost and low reuse rate of the recognition model. Specifically, training the recognition model requires a large number of training samples, and training samples in the form of "text-organization name-subdivision type" need to manually label corpus according to different extraction tasks and text fields, and construct training samples, which leads to the high cost of model training. At the same time, since each recognition model is trained with targeted training samples according to different extraction tasks and text fields, such recognition models cannot be used for other extraction tasks, nor can they be used to deal with different fields. text, which leads to a low reuse rate of the recognition model.
[0043]To this end, the present application provides a new named entity extraction method, which combines named entity recognition m...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


