Answer extraction method based on semantic dependency tree

An answer extraction, semantic technology, applied in semantic analysis, natural language data processing, special data processing applications, etc., can solve problems such as inability to obtain, without considering word frequency, syntactic structure keyword association, complex calculation, etc., to improve the accuracy rate Effect

Inactive Publication Date: 2018-09-28
NORTHWEST UNIV(CN)
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the existing semantic dependency tree-based algorithms, although more comprehensive semantic information is obtained, the calculation is extremely complicated, without considering features such as word frequency, syntactic structure, and the relationship between keywords, and often cannot achieve good results

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
  • Answer extraction method based on semantic dependency tree
  • Answer extraction method based on semantic dependency tree
  • Answer extraction method based on semantic dependency tree

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0055] In this embodiment, 5340 questions are crawled and selected from Baidu Zhizhi, one question corresponds to multiple answers, the answers of each question are broken from the original order and remixed, and the semantic dependency tree based on the present invention is used. Improve the algorithm to obtain the best answer sentence for the question sentence.

[0056] Utilize accuracy rate and MRR (mean ranking reciprocal) value to measure method performance, and method of the present invention is based on the algorithm of vector space model and original algorithm contrast based on semantic dependency tree, its result is as shown in table 1, as can be seen from table 1 , the method of the present invention comprehensively considers vector similarity, word shape similarity and dependent path length similarity, and compared with other algorithms, the accuracy rate of selecting the best answer sentence is greatly improved.

[0057] Table 1

[0058]

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 an answer extraction method based on a semantic dependency tree. The method comprises the step of selecting an optimal answer from the candidate answer sentences by comprehensive consideration of a vector similarity, a word form similarity and a dependency path length similarity on the basis of considering a semantic relation between an interrogative sentences and candidateanswer sentences. According to the method, compared with other algorithm, the accurate rate for selection of the optimal answer sentence is greatly improved.

Description

technical field [0001] The invention belongs to the field of automatic question answering (QA), and relates to an answer extraction method based on a semantic dependency tree. Background technique [0002] As a new type of search engine, automatic question answering system returns precise and concise answers to users. Its processing flow is divided into three modules: question analysis, information retrieval, and answer extraction. Among them, the answer extraction algorithm is the core research problem of the answer extraction module, and the performance of the algorithm will most directly affect the user experience of the question answering system. [0003] The basic process of the answer extraction algorithm is to take the result of the information retrieval module—the sorted paragraphs—as input, and through calculation and analysis, select an answer with the highest calculation weight, the most relevant, accurate and concise answer to the user’s question, and return it t...

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): G06F17/27G06F17/30
CPCG06F40/211G06F40/289G06F40/30
Inventor 周蕾史维峰
Owner NORTHWEST UNIV(CN)
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