Check patentability & draft patents in minutes with Patsnap Eureka AI!

Multi-relation questioning and answering system adopting interpretable reasoning network

A relational and network technology, applied in the field of artificial intelligence and the Internet, can solve problems such as being unsuitable for other operations, lack of explicit explanation by neural interrogators, etc., and achieve the effect of high interpretability

Active Publication Date: 2018-05-04
TSINGHUA UNIV
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the Neural Programmer requires predefined symbolic operations and thus may not be suitable for other operations, while the Neural Interrogator lacks explicit interpretation

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
  • Multi-relation questioning and answering system adopting interpretable reasoning network
  • Multi-relation questioning and answering system adopting interpretable reasoning network
  • Multi-relation questioning and answering system adopting interpretable reasoning network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0041]First of all, it should be noted that although Chinese or English is used as an example of natural language below, this is only for ease of understanding and does not imply any limitation. The applicable occasions of the present invention are not limited to specific language types or specific language families.

[0042] Task Definition: The goal is to provide interpretable reasoning networks to answer multi-relational questions.

[0043] Given a question q, its named entities or topics e s It can be obtained with NER (Named Entity Recognition) tools, and the task is to find an entity a in the knowledge base as an answer.

[0044] The inventors consider two typical multi-relational problems: the path problem and the join problem, and the former is the main focus of the present invention.

[0045] Path issues contain only named entities (body e s ), to find its answer (object a) along an answer path consisting of several relations and corresponding intermediate entities...

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 multi-relation questioning and answering method adopting an interpretable reasoning network. The method is implemented through a multi-hop mode. The method comprises the steps that 1, an input question is converted into distributed question expression; 2, according to a reasoning state of a previous hop and question expression of the previous hop, the relation between theprevious hop and a current hop is predicted; 3, if the predicted relation between the previous hop and the current hop is not a termination relation, the reasoning state of the previous hop and the question expression of the previous hop are updated to be a reasoning state of the current hop and question expression of the current hop according to the predicted relation between the previous hop and the current hop, the current hop serves as a next hop to return to the step 2, and otherwise the step 4 is turned to; and 4, a question and an answer of the current hop are determined and output according to the reasoning state of the current hop. The method can provide traceable and observable intermediate prediction and is used for reasoning analysis and fault diagnosis.

Description

technical field [0001] The present invention relates to the fields of artificial intelligence and Internet technology, in particular, to an (open field) multi-relational question answering system utilizing interpretable reasoning networks. Background technique [0002] Question answering system based on knowledge base is an advanced form of information retrieval system, which can answer user's question and answer query service request expressed in natural language with accurate and concise natural language. Specifically, given a natural language question, through semantic understanding and parsing of the question, and then using the knowledge base for query, the answer to the question is given by searching the knowledge database in the relevant field. [0003] Among such question answering systems, open-domain question answering (QA) has been a hot topic in the field of artificial intelligence, and large knowledge bases such as Freebase have also facilitated this task in rec...

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
CPCG06F16/3329
Inventor 黄民烈周曼桐朱小燕
Owner TSINGHUA UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com