The influence of semantic link network on the ability of question-answering system

Bei Xu; Hai Zhuge

doi:10.1016/j.future.2020.02.042

The influence of semantic link network on the ability of question-answering system

Bei Xu
, Hai Zhuge^*

^*Corresponding author for this work

Nanjing University of Posts and Telecommunications
Guangzhou University
Aston University
Chinese Academy of Sciences, Beijing

Research output: Contribution to journal › Article › peer-review

9 Citations (Scopus)

39 Downloads (Pure)

Abstract

Semantic Link Network plays an important role in representing and understanding text. This paper investigates the influence of semantic links on the basic abilities of a type of QA system that extracts answers from a range of texts (answer range). Research concerns how semantic links influence the answer range and the performance of this type of QA system. Research also concerns the ability to answering different types of questions and supporting different patterns of answering questions. Based on the semantic link network extracted from Wikipedia, an experimental QA system is developed to answer questions according to a range of pages in Wikipedia. Research reached the following results: (1) the answer range and the semantic link network influence each other: keeping a certain range of performance, increase one can decrease the request of the other; and, (2) the semantic link network can enhance the ability of QA system in answering questions and supporting patterns of answering questions covered by semantic link network.

Original language	English
Pages (from-to)	1-14
Number of pages	14
Journal	Future Generation Computer Systems
Volume	108
Early online date	19 Feb 2020
DOIs	https://doi.org/10.1016/j.future.2020.02.042
Publication status	Published - Jul 2020

Bibliographical note

Funding

Research was supported by the National Science Foundation of China (No. 61640212 , 61602256 , 61876048 , 61806101 ) and supported by the International Research Network on Cyber–Physical–Social Intelligence, China consisting of Guangzhou University, Aston University, Key Lab of Intelligent Information Processing at Institute of Computing Technology in Chinese Academy of Sciences, and University of Chinese Academy of Sciences.

Keywords

Performance of question answering system
Question answering system
Semantic link network

Access to Document

10.1016/j.future.2020.02.042

The Influence of Semantic Link Network on the Ability of Question-Answering System
© 2020, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/
Accepted author manuscript, 14.8 MBLicence: CC BY-NC-ND 3.0

Cite this

@article{6e9fd50e063b45ca875fef3512fd0533,

title = "The influence of semantic link network on the ability of question-answering system",

abstract = "Semantic Link Network plays an important role in representing and understanding text. This paper investigates the influence of semantic links on the basic abilities of a type of QA system that extracts answers from a range of texts (answer range). Research concerns how semantic links influence the answer range and the performance of this type of QA system. Research also concerns the ability to answering different types of questions and supporting different patterns of answering questions. Based on the semantic link network extracted from Wikipedia, an experimental QA system is developed to answer questions according to a range of pages in Wikipedia. Research reached the following results: (1) the answer range and the semantic link network influence each other: keeping a certain range of performance, increase one can decrease the request of the other; and, (2) the semantic link network can enhance the ability of QA system in answering questions and supporting patterns of answering questions covered by semantic link network.",

keywords = "Performance of question answering system, Question answering system, Semantic link network",

author = "Bei Xu and Hai Zhuge",

note = "{\textcopyright} 2020, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ ",

year = "2020",

month = jul,

doi = "10.1016/j.future.2020.02.042",

language = "English",

volume = "108",

pages = "1--14",

journal = "Future Generation Computer Systems",

issn = "0167-739X",

publisher = "Elsevier",

}

TY - JOUR

T1 - The influence of semantic link network on the ability of question-answering system

AU - Xu, Bei

AU - Zhuge, Hai

PY - 2020/7

Y1 - 2020/7

N2 - Semantic Link Network plays an important role in representing and understanding text. This paper investigates the influence of semantic links on the basic abilities of a type of QA system that extracts answers from a range of texts (answer range). Research concerns how semantic links influence the answer range and the performance of this type of QA system. Research also concerns the ability to answering different types of questions and supporting different patterns of answering questions. Based on the semantic link network extracted from Wikipedia, an experimental QA system is developed to answer questions according to a range of pages in Wikipedia. Research reached the following results: (1) the answer range and the semantic link network influence each other: keeping a certain range of performance, increase one can decrease the request of the other; and, (2) the semantic link network can enhance the ability of QA system in answering questions and supporting patterns of answering questions covered by semantic link network.

AB - Semantic Link Network plays an important role in representing and understanding text. This paper investigates the influence of semantic links on the basic abilities of a type of QA system that extracts answers from a range of texts (answer range). Research concerns how semantic links influence the answer range and the performance of this type of QA system. Research also concerns the ability to answering different types of questions and supporting different patterns of answering questions. Based on the semantic link network extracted from Wikipedia, an experimental QA system is developed to answer questions according to a range of pages in Wikipedia. Research reached the following results: (1) the answer range and the semantic link network influence each other: keeping a certain range of performance, increase one can decrease the request of the other; and, (2) the semantic link network can enhance the ability of QA system in answering questions and supporting patterns of answering questions covered by semantic link network.

KW - Performance of question answering system

KW - Question answering system

KW - Semantic link network

UR - https://www.scopus.com/pages/publications/85079833776

UR - https://www.sciencedirect.com/science/article/pii/S0167739X19316127?via%3Dihub

U2 - 10.1016/j.future.2020.02.042

DO - 10.1016/j.future.2020.02.042

M3 - Article

AN - SCOPUS:85079833776

SN - 0167-739X

VL - 108

SP - 1

EP - 14

JO - Future Generation Computer Systems

JF - Future Generation Computer Systems

ER -

The influence of semantic link network on the ability of question-answering system

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this