Automatic text abstracting method and device based on global semantics, medium and equipment
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology for automatic summarization and text, applied in semantic analysis, neural learning methods, unstructured text data retrieval, etc.
Active Publication Date: 2020-08-21
SOUTH CHINA UNIV OF TECH
View PDF9 Cites 4 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
However, there are still many problems in generative text summarization, such as unsound semantics, grammatical errors, repeated words in context, etc.
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 more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0075] In this embodiment, a text automatic summarization method based on global semantics, the process is as follows figure 1 shown, including the following steps:
[0076] S1. Preprocess the content of the original text, write a script to divide the original text into bytes, and replace the uppercase letters with lowercase letters to obtain text information.
[0077] S2, input the preprocessed text information to the encoder, the encoder globally encodes the text information based on the convolutional neural network and the self-attention mechanism, and screens through a control unit to obtain the final encoded output result, such as figure 2 shown.
[0078] Specifically, step S2 includes the following sub-steps:
[0079] S21, sequentially receive the word embedding of each word from the text information, import it into a bidirectional LSTM network, and output the result at each time node t i=0,1,2...n, n is the number of encoded information.
[0080] output result f...
Embodiment 2
[0132] A storage medium in this embodiment is characterized in that the storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the global semantics-based automatic text processing described in Embodiment 1. Abstract method.
Embodiment 3
[0134] In this embodiment, a computing device includes a processor and a memory for storing a program executable by the processor. It is characterized in that, when the processor executes the program stored in the memory, the text based on global semantics described in Embodiment 1 is implemented. Automatic summarization method.
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 an automatic text abstracting method and device based on global semantics, a medium and equipment. The method comprises the following steps: preprocessing the content of an original text, dividing the content according to bytes, and replacing capital letters in the original text with lowercase letters to obtain text information; by an encoder, performing global encoding on the text information based on a convolutional neural network and a self-attention mechanism, and performing screening through a control unit to obtain a final encoding output result; and by the decoder, decoding the encoded output result based on a repetitive punishment mechanism and generating a text summary. According to the method, a convolution filter is added to athe encoder, and the repetitive punishment mechanism is used in the decoder part to further suppress repetitive words so that the smoothness of abstract text semantics can be improved, the repeated punishment mechanism can greatlyinhibit already appeared words, the repeatability problem of abstract generation is reduced, and therefore the readability of abstract generation is improved.
Description
technical field [0001] The present invention relates to the technical field of natural language processing, and more specifically, relates to a method, device, medium and equipment for automatic text summarization based on global semantics. Background technique [0002] With the rapid development of the Internet, how to quickly and accurately read a large amount of information makes the in-depth study of automatic text summarization technology a necessary requirement. As a technology that can alleviate information overload, automatic text summarization has been widely used in practice, such as automatically generating summaries of news articles and technical articles, automatically generating snapshots of search engine retrieval results, automatic writing robots, and so on. [0003] Automatic text summarization technology is to use computer to automatically extract the central idea and key content from the original article, and perform semantic analysis and processing to gen...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.