Remote supervision relation extraction method based on multilayer attention mechanism
A remote supervision and relationship extraction technology, applied in the fields of artificial intelligence and natural language processing, can solve problems such as poor extraction effect, ignoring sentence package noise processing, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0028] The method of the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. This embodiment describes in detail the method and effect of this method when it is implemented in the mainstream data set of relation extraction.
[0029] Such as figure 1 As shown, a method of distant supervision relation extraction based on multi-layer attention mechanism, including the following steps:
[0030] Step 1: Obtain the knowledge base and divide the sentences in the knowledge data set into packages.
[0031] Specifically, the sentences in the knowledge dataset are divided into packages according to the corresponding entity pairs, so that the sentences in the packages have the same entity pairs, and the relationship corresponding to the entity pairs is assigned to each sentence.
[0032] Step 2: Obtain the matrix representation of the sentence.
[0033] details as follows:
[0034] First, let the i-th package in th...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


