Domain named entity denoising method and system based on entity topic association degree
A named entity and named entity recognition technology, which is applied in the fields of instruments, electrical digital data processing, calculation, etc., can solve the problems that affect the user's experience of using the map, and achieve the effect of improving user experience and improving accuracy
Pending Publication Date: 2020-11-20
BEIJING MININGLAMP SOFTWARE SYST CO LTD
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] However, because the named entity recognition model cannot achieve 100% accuracy, in the construction of the map, non-domain entities that are often misrecognized are often mixed in, which affects the user's experience in using the map.
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
[0044] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them.
[0045] It should be noted that all directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relationship between the components in a certain posture (as shown in the accompanying drawings). Relative positional relationship, movement conditions, etc., if the specific posture changes, the directional indication will also change accordingly.
[0046] In addition, the descriptions involving "first", "second" and so on in the present invention are only for descriptive purposes, and should not be understood as indicating or implying their relative importance or implicitly ind...
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 provides a domain named entity denoising method and system based on entity topic correlation. The method comprises steps of S1, obtaining a to-be-recognized corpus, carrying out the entity recognition through a named entity recognition model, and obtaining an entity list; S2, splitting each named entity in the entity list into semantic elements, and obtaining a plurality of domain-related topics and weights thereof through a similar semantic element model; S3, calculating to obtain a score of the named entity based on each domain-related theme obtained in the step S2 and the weight of the theme; and S4, setting a noise threshold, screening according to the noise threshold, and filtering noise entities in the named entities. According to the domain named entity denoising method and the domain named entity denoising system adopting the scheme, noise identification filtering is performed on the identified named entities, and entities which are incorrectly identified and areirrelevant to the domain are removed, so correct entities are reserved to construct a knowledge graph.
Description
technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to a method and system for denoising domain named entities based on entity topic relevance. Background technique [0002] Named Entity Recognition (nER for short), also known as "proper name recognition", refers to the recognition of entities with specific meanings in texts, mainly including names of people, places, institutions, and proper nouns. [0003] Named entity recognition is a basic step in building a knowledge graph. In the knowledge graph construction, named entities constitute the points in the graph, and the relationships between entities constitute the edges in the graph. In addition, entities in the same field have a large number of similar semantic elements, and different types of semantic elements usually mean entities in different fields. For example, the similar semantic elements of "Huawei Smart Screen" include "smart", "eye protectio...
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 IPC IPC(8): G06F40/295
CPCG06F40/295
Inventor 闫峰卫海天丁若谷
Owner BEIJING MININGLAMP SOFTWARE SYST CO LTD