Method, system and device for Chinese named entity recognition based on self-attention mechanism
A named entity recognition and attention technology, applied in natural language data processing, instruments, computing and other directions, can solve the problem that the accuracy of Chinese named entity recognition cannot meet the needs, and achieve the effect of improving the accuracy
Active Publication Date: 2020-08-11
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problem that the accuracy of Chinese named entity recognition cannot meet the demand, the first aspect of the present invention proposes a Chinese named entity recognition method based on a self-attention mechanism, including :
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
[0040] The application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain related inventions, rather than to limit the invention. It should also be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.
[0041] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.
[0042] Currently, the publicly available data sets for Chinese named entity recognition tasks are small, and the performance of the proposed methods is not particularly high. In contrast, there are more relevant data sets in the field of Chinese word segmentation tasks, and there are many similarities between Chinese named entity recognition tasks and Chinese word segmentation tasks.
[0043...
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 belongs to the technical field of natural language processing, particularly relates to a Chinese named entity recognition method, system and device based on a self-attention mechanism, and aims to solve the problem that the accuracy of Chinese named entity recognition cannot meet the requirement. The method comprises the following steps: extracting a private feature h1 and a common feature s1 of a to-be-identified statement; calculating a long-distance dependency relationship corresponding to the common feature s1 and the private feature h1 based on a self-attention mechanism, and obtaining a private feature h'1 based on the dependency relationship and a common feature s'1 based on the dependency relationship; when the to-be-identified statement is judged to be the Chinese named entity identification data or not through the task classifier, h'1 and s'1 are spliced, the fused Chinese named entity identification data feature h'1 is obtained, and tag prediction is conductedon the fused feature h'1 through a conditional random field. According to the invention, the accuracy of Chinese named entity identification is effectively improved.
Description
technical field [0001] The invention belongs to the technical field of natural language processing, and in particular relates to a Chinese named entity recognition method, system and device based on a self-attention mechanism. Background technique [0002] With the vigorous development and increasing popularity of the Internet, massive amounts of information are generated every day in every field, such as entertainment, sports and other fields. Due to the unstructured and disordered nature of this information, how to help people understand these data and quickly identify useful information from massive unstructured texts, thereby reducing the cost of human learning, is an urgent problem to be solved. . Information extraction technology is formally designed to solve this problem. [0003] The task of named entity recognition is an important part of information extraction technology, and it is one of the important basic tasks and difficult problems in the field of informatio...
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): G06F40/295G06F40/289
Inventor 陈玉博刘康赵军曹鹏飞
Owner INST OF AUTOMATION CHINESE ACAD OF SCI