Construction method, device and storage medium of entity-relationship extraction model
A technology of entity relationship and construction method, which is applied in the direction of database model, relational database, structured data retrieval, etc., can solve the problem of low accuracy of the extraction model, and achieve the effect of high accuracy
Active Publication Date: 2021-08-31
SOUTH CENTRAL UNIVERSITY FOR NATIONALITIES
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The main purpose of the present invention is to provide a construction method, device and storage medium of an entity relationship extraction model, aiming to solve the problem of low accuracy of the constructed entity relationship extraction model
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
no. 1 example
[0044] refer to figure 2 , a first embodiment of a method for constructing an entity-relationship extraction model, comprising the following steps:
[0045] Step S202, extracting a plurality of sample sentence groups from the sample corpus, each sample sentence group includes an entity sentence, a relational sentence, the preceding sentence of the entity sentence, and the following sentence of the entity sentence, and the entity sentence contains the sample A statement of a sample entity pair in a triple, where the relationship statement is a statement used to describe the entity relationship of the sample entity pair;
[0046] Wherein, the sample corpus includes sample corpus and multiple sample triples corresponding to the sample corpus. The sample corpus can be stored in the memory of the terminal, and can also be stored in an external device communicatively connected with the terminal. The sample corpus contains multiple sample entities, and different sample entities ha...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for constructing an entity relationship extraction model, comprising: extracting a plurality of sample sentence groups from a sample corpus, each sample sentence group respectively including an entity sentence, a relation sentence, the preceding sentence of the entity sentence, and the The latter sentence of the entity sentence; each sample sentence group is encoded separately to obtain a plurality of sample sentence vector groups; each sentence vector in each sample sentence vector group is combined to assign weights to different entity sentence vectors in each sample sentence vector group ; Generating entity statement set vectors according to entity statement vectors and corresponding weights in each sample statement vector group; training a preset neural network model through said entity statement set vectors to obtain an entity relationship extraction model. The invention also discloses a construction device and a storage medium for an entity relationship extraction model. The entity-relationship extraction model constructed by the invention has high accuracy when used for entity-relationship extraction.
Description
technical field [0001] The present invention relates to the technical field of data mining, in particular to a method, device and storage medium for constructing an entity relationship extraction model. Background technique [0002] Relationship extraction is a task based on entity recognition, and its core is to extract the relationship between entity pairs contained in a sentence. Generally, an entity relationship extraction model is used to extract the entity relationship from the corpus to be tested. Distant supervision is a relatively common practice in building a relationship extraction model. It assumes that if the entity pairs contained in the sentences in the training corpus have a relationship in the corpus, then we think that all sentences containing the same entity pairs in the corpus express this relationship. But using this assumption will lead to a lot of noise data, because an entity pair has a unique entity relationship by default, and a sentence containin...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/21G06F16/28
CPCG06F16/212G06F16/288
Inventor 刘晶李蔚栋覃俊李子茂王江晴吴经龙孟凯
Owner SOUTH CENTRAL UNIVERSITY FOR NATIONALITIES