Named entity recognition model training method and device and named entity recognition method and device
A named entity recognition and model training technology, applied in the field of data processing, can solve the problems of low accuracy of recognition results and poor word segmentation effect of Chinese scientific papers, and achieve the effect of improving accuracy, improving accuracy and efficient capture
Active Publication Date: 2021-08-13
BEIJING UNIV OF POSTS & TELECOMM
View PDF6 Cites 6 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Embodiments of the present invention provide a named entity recognition model training method, recognition method and device, to eliminate or improve one or more defects in the prior art, and to solve the poor word segmentation effect of Chinese scientific papers, resulting in accurate recognition results low rate problem
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
[0036] In order to make the objects, technical solutions, and advantages of the present invention, the present invention will be further described in detail below in connection with the embodiments and drawings. Here, a schematic embodiment of the present invention will be described herein for explanation of the invention, but is not limited to the present invention.
[0037] Here, it is also necessary to prevent the present invention in order to avoid unnecessary details, only the structural and / or processing steps associated with the approach according to the present invention, and omitted Additional details of the relationship of the present invention.
[0038] It should be emphasized that the terms "including / comprise" presence, feature, elements, steps, or components, but does not exclude one or more other features, elements, steps, or components presence or addition.
[0039] Name entity recognition can use statistical machine learning methods, this first requires superv...
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 named entity recognition model training method, a named entity recognition method and a named entity recognition device, and an initial neural network model of the model training method carries out vector representation on science and technology paper data by combining key character level codes and word level codes; the character level vector and the word level vector are introduced into the bidirectional long-short-term memory network, so that the context relation can be mined, the semantic features of keywords are mined at the same time, and the accuracy of word segmentation boundaries is improved; by introducing the character level vector into the self-attention mechanism model, the internal correlation of the data can be captured more efficiently, and the accuracy of named entity recognition is improved.
Description
Technical field [0001] The present invention relates to the field of data processing, and more particularly to a nomenclature, identification method, and apparatus for identifying an entity identification model. Background technique [0002] Science and technology data can be defined as massive data generated by research-related activities, which has the characteristics of large data size, professional, and a wide variety of content. The scientific academic conference data contains a collection of papers in a certain field. The construction of portraits in the academic conference can help researchers quickly obtain valuable research information, and the core of building portraits is identified for naming entities. [0003] Named Entity Recognition, Ner is an important research direction in the field of natural language processing, and its purpose is to classify the entities in the given text in a predefined category, which is a sequence annotation problem. The naming entity ident...
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 Applications(China)
IPC IPC(8): G06F40/126G06F40/295G06F40/30G06N3/04G06N3/08
CPCG06F40/126G06F40/295G06F40/30G06N3/08G06N3/044G06N3/045
Inventor 杜军平于润羽薛哲徐欣
Owner BEIJING UNIV OF POSTS & TELECOMM