Establishment method of relation extraction model and relation extraction method
A technology of relation extraction and method establishment, applied in neural learning methods, biological neural network models, instruments, etc., can solve problems such as training data noise and seriousness
Active Publication Date: 2022-02-01
北京中科凡语科技有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, there is a serious problem with the training data generated by this remote supervision, that is, the generated training data is very noisy, because not all sentences containing two entities will reflect the relationship between them
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
Embodiment Construction
[0041] The present disclosure will be further described in detail below with reference to the drawings and embodiments. It can be understood that the specific implementation manners described here are only used to explain relevant content, rather than to limit the present disclosure. It should also be noted that, for ease of description, only parts related to the present disclosure are shown in the drawings.
[0042] It should be noted that, in the case of no conflict, the implementation modes and the features in the implementation modes in the present disclosure can be combined with each other. The technical solutions of the present disclosure will be described in detail below with reference to the accompanying drawings and in combination with implementation manners.
[0043] Unless otherwise specified, the illustrated exemplary embodiments / embodiments are to be understood as exemplary features providing various details of some manner in which the technical idea of the pre...
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 present disclosure provides a method for establishing a relationship extraction model, including: preprocessing text samples marked with entities, entity categories, and relationship categories; extracting multiple sentences containing the same entity pair from the labeled text samples as a statement package, Obtain the sentence package group of the text sample; based on the entity directed acyclic graph of the text sample and the marked text sample entity, obtain the candidate entity category of each entity and the parent category of the candidate entity category; the relationship based on the text sample is directed Acyclic graph and the candidate entity category and parent category of each entity, obtain the candidate relationship of the entity pair and the parent relationship of the candidate relationship; use TextCNN to obtain multi-layer multi-classification loss; use hierarchical attention network to obtain hierarchical attention loss; A relation extraction model is constructed based on hierarchical multi-classification loss and hierarchical attention loss, and the relation extraction model is trained with the marked relation category as the training target.
Description
technical field [0001] The disclosure relates to a method for establishing a relationship extraction model and a relationship extraction method, and belongs to the technical fields of natural language processing and information extraction. Background technique [0002] With the rapid development of communication technology and Internet technology, the explosive growth of data generated on the network every day, more and more noise is encountered when using string indexing and retrieval data, how to use semantics to define data, from massive data Efficiently obtaining valuable information and knowledge has gradually become an increasingly urgent need. It is a difficult problem in the field of natural language processing to automatically structure the data, remove the false and preserve the true, and convert the information in the data into verified knowledge. [0003] In this context, knowledge graphs defined in semantic form and stored in knowledge form came into being. Man...
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): G06F16/35G06F40/295G06N3/04G06N3/08
CPCG06F16/353G06F40/295G06N3/08G06N3/045
Inventor 周玉
Owner 北京中科凡语科技有限公司