A method and system for detecting missing words based on fine-tuning generative confrontation network model
A network model and detection method technology, applied in biological neural network models, neural learning methods, instruments, etc., can solve problems such as difficulty in determining
Active Publication Date: 2022-02-11
京华信息科技股份有限公司
View PDF12 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
But if the whole word is gone, for example, if the sentence is "optimization work" at this time, it is difficult to determine what word should be used later, and the probability calculation and pre-screening of matching collocations become a technical 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
[0056] The idea, specific structure and technical effects of the present invention will be clearly and completely described below in conjunction with the embodiments and accompanying drawings, so as to fully understand the purpose, scheme and effect of the present invention. 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.
[0057] In the description of the present invention, several means one or more, and multiple means two or more. Greater than, less than, exceeding, etc. are understood as not including the original number, and above, below, within, etc. are understood as including the original number. If the description of the first and second is only for the purpose of distinguishing the technical features, it cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implic...
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 invention provides a method and system for detecting missing words based on a fine-tuning generative confrontational network model. The text corpus to be detected is preprocessed into a sequence composed of multiple word segments, and the word segments in the sequence are read according to the vocabulary of ERNIE. Take it as the embedding vector Embedding, combine the embedding vector Embedding of multiple word segmentations to form the vector sequence Eseq, use the distance formula to calculate the distance between the generated sequence and the standard sequence as the threshold, and preprocess the sequence to be detected to obtain the input sequence to be detected. The detection input sequence is input into the generation network to obtain the generated sequence to be detected, and the distance between the generated sequence to be detected and the standard sequence is compared with the threshold value. If it is greater than the threshold value, there are missing words, which achieves the goal of detecting abnormalities in the text sequence quickly and at low computational cost. Effect.
Description
technical field [0001] The invention belongs to the field of artificial intelligence, and in particular relates to a method and system for detecting missing words based on a fine-tuning generative confrontation network model. Background technique [0002] The detection of missing words is mainly aimed at near sound and shape, as well as one missing word and one extra word. For one word missing or one more word, for example, the last word "process" in "optimize workflow" is missing a word "cheng". The main basis for proofreading is to select words containing "flow" from the candidate words. But if the whole word is gone, for example, if the sentence is "optimization work" at this time, it is difficult to determine what word should be used later, and the probability calculation and pre-screening of matching collocations become a technical problem. Contents of the invention [0003] The purpose of the present invention is to propose a method and system for detecting missing ...
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): G06F40/284G06F40/216G06F40/237G06N3/04G06N3/08
CPCG06F40/284G06F40/237G06F40/216G06N3/08G06N3/045
Inventor 蓝建敏申鑫
Owner 京华信息科技股份有限公司