Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Chinese natural language interrogative sentence semantization knowledge base automatic question-answering method

A natural language question and natural language technology, applied in the field of automatic question answering of knowledge bases with semantic Chinese natural language questions, can solve problems such as low query structure and inability to realize accurate and efficient query of knowledge base data, and achieve easy Detectable, understandable and manageable effects

Active Publication Date: 2016-06-22
NANJING UNIV
View PDF3 Cites 137 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the process of automatic question answering based on the knowledge base, after the user inputs a Chinese natural language question sentence, the traditional method only adopts simple processing to obtain the keywords for the question sentence. Inquire

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
  • Chinese natural language interrogative sentence semantization knowledge base automatic question-answering method
  • Chinese natural language interrogative sentence semantization knowledge base automatic question-answering method
  • Chinese natural language interrogative sentence semantization knowledge base automatic question-answering method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] specific implementation

[0019] The invention discloses an automatic question answering method for a knowledge base based on template extraction and semanticization of Chinese natural language questions. Identify and expand to generate a semantic dependency tree; then use the generalized template and semantic analysis technology based on statistical learning to obtain the time, space, fact subject, fact object and other components in the question sentence, and then carry out semantic processing to extract the question All event-related component element attributes and their values ​​in the sentence generate multiple "attribute-value" pairs, in which the elements to be answered are replaced by interrogative words to form a set of complex fact triples; The tuples are combined with other related fact triples to form a knowledge base query with constraints, and the query matching based on similarity calculation is performed in the knowledge base, and the results are extrac...

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 discloses a Chinese natural language interrogative sentence semantization knowledge base automatic question-answering method. The method includes the following steps that Chinese natural language processing is performed on a fact type question input by a user, word segmentation, part-of-speech tagging and identification and expanding of a named entity are achieved, and a semantic dependency tree is generated; a generalization template and a semantic analysis technology are used for acquiring time, space, a fact entity, a fact object and the like in an interrogative sentence, then semantic processing is performed, composition element attributes relevant to all events in the interrogative sentence and values of the attributes are extracted, a plurality of 'attribute-value' pairs are generated, to-be-answered elements are substituted by interrogatives, and a complex fact triple set is formed; after a triple where a to-be-answered part is located is combined with other relevant fact triple sets to form knowledge base query with conditional constraints, and query matching based on similarity calculation is performed in a knowledge base, a result is extracted from the knowledge base, and a final answer is obtained. Fast and accurate query response to the knowledge base is achieved.

Description

technical field [0001] The present invention relates to Semantic Web, natural language processing and automatic question answering technology, in particular to a knowledge base automatic question answering method for semanticizing Chinese natural language questions, specifically a knowledge base for semanticizing Chinese natural language questions based on template extraction An automatic question answering method, especially a knowledge base automatic question answering method for fact-oriented questions by transforming the semantics of Chinese natural language question sentences into a knowledge base query for template extraction. Background technique [0002] Semantic Web is an important development direction of the World Wide Web, which provides the basis for knowledge representation, reasoning, exchange and reuse on the World Wide Web. The Semantic Web uses a set of "attribute-value" to describe the entity (entity), and a single "attribute-value" pair can be expressed a...

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): G06F17/30
CPCG06F16/3335G06F16/3344G06F16/36
Inventor 胡伟姜成樾程龚瞿裕忠
Owner NANJING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com