Medical consultation named entity identification method based on adversarial multi-task learning
A technology for named entity recognition and multi-task learning, which is applied in the fields of instruments, electrical digital data processing, computing, etc. It can solve problems such as effect dependence and training data set size, and achieve the effect of improving the effect.
Active Publication Date: 2020-06-02
SOUTH CHINA UNIV OF TECH
View PDF6 Cites 12 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Although deep learning can extract data features better, its effect often depends on the size of the training data set.
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
[0051] The specific implementation of the present invention will be further described below in conjunction with the accompanying drawings and specific embodiments. It should be pointed out that the described embodiments are only a part of the embodiments of the present invention, not all the embodiments.
[0052] like figure 1 As shown, a medical consultation named entity recognition method based on adversarial multi-task learning includes the following steps:
[0053] Step 1. Collect medical consultation data, preprocess the medical consultation data, and label some of the data as entities to obtain labeled medical consultation data;
[0054] The collected medical consultation data includes the questions asked by the patient or the patient's family members to the doctor and the doctor's answers to the questions. The preprocessing adopted includes cleaning the noise data, removing useless symbols, and word segmentation. The labeled entities include body parts, sympto...
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 medical consultation named entity identification method based on adversarial multi-task learning. The method comprises the following steps: collecting medical consultation data, preprocessing the medical consultation data, and performing entity labeling on a part of the data to obtain labeled medical consultation data; constructing a bidirectional language model and a mask language model, and respectively pre-training the bidirectional language model and the mask language model by utilizing unlabeled medical consultation data; introducing pre-training features of thebidirectional language model and the mask language model into a named entity recognition model; performing adversarial multi-task training on the named entity recognition model to obtain a trained named entity recognition model; and inputting a section of text into the target labeling model of the trained named entity recognition model to realize text named entity recognition. According to the method, technologies such as transfer learning, adversarial learning and multi-task learning are introduced, and the medical consultation text named entity recognition effect is effectively improved.
Description
technical field [0001] The invention relates to the technical field of natural language processing, in particular to a medical consultation named entity recognition method based on adversarial multi-task learning. Background technique [0002] In recent years, with the rapid development and popularization of Internet technology, more and more patients choose to consult doctors online through online medical websites, such as Qiuyi.com, Xunyiwenwang.com, and Family Doctor Online. Consulting medical and health-related issues, this method is more efficient and convenient to promote medical and health exchanges between doctors and patients. However, due to the relatively small number of doctors currently participating in online medical question-and-answer services, many patients often cannot get timely professional responses to online medical consultations. At the same time, with the development and maturity of artificial intelligence technology in natural language processing, m...
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): G06F40/295
CPCY02A90/10
Inventor 文贵华陈河宏李杨辉
Owner SOUTH CHINA UNIV OF TECH