Automatic text summarization generation method and automatic text summarization generation system based on temporal knowledge extraction
A technology of knowledge extraction and automatic generation, applied in the fields of natural language data processing, instruments, computing, etc., can solve the problem of unsatisfactory readability of end users, and achieve the effect of improving coherence
Inactive Publication Date: 2016-10-26
SHANDONG UNIV
View PDF4 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Although these semantic triples can concisely summarize the content of the text, their readability for end users is not very ideal
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 following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. The present invention takes a given biography of a Wikipedia character as an example:
[0052] figure 1 It is a schematic flow chart of a method for automatically generating text summaries based on temporal knowledge extraction in the present invention, as shown in figure 1 As shown, the method includes the following steps:
[0053]Step 1: Extract seed facts, candidate facts and patterns indicating the relationship of the candidate facts respectively from the text.
[0054] Among them, step 1: extract the seed facts from the structured / semi-structured data of the text, and extract the candidate facts and their affiliation patterns from the text;
[0055] In step 1, seed facts are extracted from structured / semi-structured data (such as information boxes and tables in Wikipedia...
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 an automatic text summarization generation method and an automatic text summarization generation system based on temporal knowledge extraction. The automatic text summarization generation method includes: extracting seed facts, candidate facts and modes indicating relations which candidate facts belong to from texts; filtering the extracted modes according to co-occurrence frequencies of every mode and the seed facts in the texts; constructing a graph structure by taking the candidate facts and the filtered modes as nodes, wherein the sides of the graph structure include connection lines between the candidate facts and the filtered modes as well as connection lines between similar filtered modes; screening out the seed facts from the candidate facts, and labeling the residual candidate facts from the graph structure according to a label propagation algorithm and the screened seed facts; sequencing the labeled candidate facts according to a timing sequence, automatically converting the sequenced labeled candidate facts into characters in the form of natural language descriptions by mechanical application of a language description template and generating a text summarization finally. The automatic text summarization generation method is capable of improving coherence of text summarizations.
Description
technical field [0001] The invention belongs to the technical field of automatic generation of text summaries, and in particular relates to a method and system for automatically generating text summaries based on temporal knowledge extraction. Background technique [0002] The existing automatic text summarization technology basically uses sentences extracted from the text, and does not really summarize the content to form a summary. When the length of the abstract is limited, it is difficult to fully cover the content simply by extracting sentences. Therefore, it is necessary to abstract the content under the condition of understanding the content. [0003] In recent years, the semantic information extraction technology of large-scale text has become more and more mature. In particular, there are more and more open information extraction tools that can extract semantic triples from text. Although these semantic triples can concisely summarize the content of the text, the...
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 IPC IPC(8): G06F17/27
CPCG06F40/258
Inventor 王雅芳任昭春
Owner SHANDONG UNIV