Entity linking method for Chinese knowledge graph question-answering system

A knowledge map and question answering system technology, applied in the field of natural language processing, can solve problems such as the replacement and use of words that cannot have similar semantics, achieve the effects of improving accuracy, improving effectiveness, and solving training data redundancy

Active Publication Date: 2020-08-21
NORTHWESTERN POLYTECHNICAL UNIV
View PDF9 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the entity linking method based on the neural network only uses the entity description information to expand the entity semantics in the entity representation, and does not consider the interchangeability of words with similar semantics in the same language environment, and cannot combine words with similar semantics in the context Replace use in

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
  • Entity linking method for Chinese knowledge graph question-answering system
  • Entity linking method for Chinese knowledge graph question-answering system
  • Entity linking method for Chinese knowledge graph question-answering system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0076] Such as figure 1 As shown, the Chinese knowledge graph question answering system includes: a Web service interaction module, a question preprocessing module, an entity link module, a query statement generation module, and a knowledge graph query module. The Web service interaction module displays the visual structural information of relevant entities in the knowledge graph, providing users with a friendly interface for interaction; the question preprocessing module performs word segmentation, part-of-speech recognition, and named entity recognition on natural language questions, and extracts questions. Useful information in the sentence; the entity link module performs similarity matching on the entities in the candidate entity list in turn, and finds the knowledge graph entity that best matches the reference item of the natural language question to determine the subject of the SPARQL query; the query language generation module converts the natural language It is conver...

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

The invention provides an entity linking method for a Chinese knowledge graph question-answering system. The method comprises the following steps: firstly, performing joint embedding on words and entities in a training corpus to obtain joint embedding vectors of the words and the entities; for an input text of the Chinese knowledge graph question-answering system, firstly, recognizing entity reference items in the input text, and determining a candidate entity list according to the entity reference items; and constructing an entity link model based on an LSTM network, performing vector splicing on the entity representation vector and the entity reference item representation vector to obtain a similarity score of the entity reference item and the candidate entity, and finally obtaining a score rank of the candidate entity, thereby selecting the candidate entity with the highest score as a target entity corresponding to the entity reference item. According to the method, the defect of link model training data redundancy caused by diversity of user questioning modes is effectively solved, and words with similar semantics can be replaced and used in the context, so that the link effectiveness is improved, and the accuracy of a question and answer system is improved.

Description

technical field [0001] The invention belongs to the field of natural language processing, and in particular relates to an entity linking method. Background technique [0002] As a new type of knowledge acquisition technology, knowledge graph has laid a solid foundation for the development of intelligent question answering by virtue of its powerful semantic expression ability and logical reasoning ability. Through the knowledge map, the semantic description of the text content of objective facts is carried out, the relationship between entities is extracted from unstructured text, and the text is transformed into an interconnected graph structure, so that the computer can truly understand the content. . However, due to its huge data capacity and complex data structure, it is difficult for ordinary users to access the knowledge in it. To solve this problem, a question answering system based on knowledge graph is proposed. Its goal is to automatically convert users' natural ...

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 Applications(China)
IPC IPC(8): G06F16/332G06F16/36G06N3/04
CPCG06F16/3329G06F16/367G06N3/045G06N3/044
Inventor 蒋泽军王丽芳陆新宇张智凯李荣涵赵孟杜承烈刘志强尤涛陈进朝
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap