Unlock instant, AI-driven research and patent intelligence for your innovation.

A Character Representation-Oriented Extraction Method of News Text Occurrence Location

A place and news technology, applied in the field of character representation-oriented news text place extraction, can solve the problems of lack of semantic structure information analysis, difficulty in distinguishing news place names from multiple place names, etc., and achieve high accuracy, high recognition rate and high accuracy. The effect of robustness

Active Publication Date: 2021-10-29
HARBIN INST OF TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above problems, the present invention proposes a character representation-oriented news text location extraction method to solve the lack of semantic structure information analysis in the existing named entity recognition algorithm in the process of character representation, resulting in the occurrence of multiple place names in the news text. Difficult to tell where the news happened

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
  • A Character Representation-Oriented Extraction Method of News Text Occurrence Location
  • A Character Representation-Oriented Extraction Method of News Text Occurrence Location
  • A Character Representation-Oriented Extraction Method of News Text Occurrence Location

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] Exemplary embodiments of the present invention will be described below with reference to the accompanying drawings. In the interest of clarity and conciseness, not all features of an actual implementation are described in this specification. It should be understood, however, that in developing any such practical embodiment, many implementation-specific decisions must be made in order to achieve the developer's specific goals, such as meeting those constraints related to the system and business, and those Restrictions may vary from implementation to implementation. Furthermore, it should be understood that development work, while potentially complex and time-consuming, would nevertheless be a routine undertaking for those skilled in the art having the benefit of the teachings herein. Here, it should also be noted that, in order to avoid obscuring the present invention due to unnecessary details, only the device structure and / or processing steps closely related to the so...

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

No PUM Login to View More

Abstract

A character representation-oriented method for extracting news text place of occurrence, which belongs to the field of information extraction, is used to solve the lack of semantic structure information analysis in the existing named entity recognition algorithm in the process of character representation, which makes it difficult to distinguish when multiple place names appear in the news text The question of where the news happened. The technical points of the present invention include: preprocessing the news text in the news text data set; labeling the entities and entity categories, paragraph features, sentence features, and word features in the preprocessed news text; The place name relationship is extracted to construct a new place name entity knowledge map; and the deep forest algorithm gcForest is used to predict and extract news occurrence places in the news text data set. The present invention can be used for characteristic characterization of people related to news events.

Description

technical field [0001] The invention relates to the field of information extraction, in particular to a character representation-oriented extraction method for news text occurrences. Background technique [0002] At present, many researchers have conducted extensive research on the extraction of event locations. Among them, some researchers who study political science have put forward some relevant research results. For example, in some related work, the author used Russia's North Caucasus crime data and Mau Mau rebellion data as data sets to analyze the relationship between the place where the event occurred and political events. The place name dictionary is used as the basis for the analysis of the place where the event occurred. The advantage of this method is that the accuracy of location recognition is improved, but the disadvantage is that if there is a place name that does not exist, it cannot be recognized, and the model is difficult to use in other places. reused ...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/9537G06F16/29G06F40/295G06F40/30G06N3/04G06N3/00
CPCG06F16/9537G06F16/29G06F40/295G06F40/30G06N3/006G06N3/044G06N3/045
Inventor 张宏莉关皓天王星方滨兴杨语晨方依孟超
Owner HARBIN INST OF TECH