Natural language user interface for fuzzy scope queries

Yan Huang, Hongfeng Yu, Wei Dong Geng, Yun He Pan

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper presents a two-agent framework to build a natural language query interface for IC information system, focusing more on scope queries in a single English sentence. The first agent, parsing agent, syntactically processes and semantically interprets natural language sentence to construct a fuzzy structured query language (SQL) statement. The second agent, defuzzifying agent, defuzzifies the imprecise part of the fuzzy SQL statement into its equivalent executable precise SQL statement based on fuzzy rules. The first agent can also actively ask the user some necessary questions when it manages to disambiguate the vague retrieval requirements. The adaptive defuzzification approach employed in the defuzzifying agent is discussed in detail. A prototype interface has been implemented to demonstrate the effectiveness.

Original languageEnglish (US)
Pages (from-to)152-161
Number of pages10
JournalJournal of Zhejiang University: Science
Volume4
Issue number2
StatePublished - Mar 1 2003

Fingerprint

User interfaces
Query languages
Fuzzy rules
Interfaces (computer)
Information systems

Keywords

  • Fuzzy rule
  • Grammar
  • Integrated circuit information system
  • Matching degree
  • Natural language user interface

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Natural language user interface for fuzzy scope queries. / Huang, Yan; Yu, Hongfeng; Geng, Wei Dong; Pan, Yun He.

In: Journal of Zhejiang University: Science, Vol. 4, No. 2, 01.03.2003, p. 152-161.

Research output: Contribution to journalArticle

Huang, Y, Yu, H, Geng, WD & Pan, YH 2003, 'Natural language user interface for fuzzy scope queries', Journal of Zhejiang University: Science, vol. 4, no. 2, pp. 152-161.
Huang, Yan ; Yu, Hongfeng ; Geng, Wei Dong ; Pan, Yun He. / Natural language user interface for fuzzy scope queries. In: Journal of Zhejiang University: Science. 2003 ; Vol. 4, No. 2. pp. 152-161.
@article{9708ceae6f0c48438b650a8ebe7f43aa,
title = "Natural language user interface for fuzzy scope queries",
abstract = "This paper presents a two-agent framework to build a natural language query interface for IC information system, focusing more on scope queries in a single English sentence. The first agent, parsing agent, syntactically processes and semantically interprets natural language sentence to construct a fuzzy structured query language (SQL) statement. The second agent, defuzzifying agent, defuzzifies the imprecise part of the fuzzy SQL statement into its equivalent executable precise SQL statement based on fuzzy rules. The first agent can also actively ask the user some necessary questions when it manages to disambiguate the vague retrieval requirements. The adaptive defuzzification approach employed in the defuzzifying agent is discussed in detail. A prototype interface has been implemented to demonstrate the effectiveness.",
keywords = "Fuzzy rule, Grammar, Integrated circuit information system, Matching degree, Natural language user interface",
author = "Yan Huang and Hongfeng Yu and Geng, {Wei Dong} and Pan, {Yun He}",
year = "2003",
month = "3",
day = "1",
language = "English (US)",
volume = "4",
pages = "152--161",
journal = "Journal of Zhejinag University: Science",
issn = "1009-3095",
publisher = "Zhejiang University Press",
number = "2",

}

TY - JOUR

T1 - Natural language user interface for fuzzy scope queries

AU - Huang, Yan

AU - Yu, Hongfeng

AU - Geng, Wei Dong

AU - Pan, Yun He

PY - 2003/3/1

Y1 - 2003/3/1

N2 - This paper presents a two-agent framework to build a natural language query interface for IC information system, focusing more on scope queries in a single English sentence. The first agent, parsing agent, syntactically processes and semantically interprets natural language sentence to construct a fuzzy structured query language (SQL) statement. The second agent, defuzzifying agent, defuzzifies the imprecise part of the fuzzy SQL statement into its equivalent executable precise SQL statement based on fuzzy rules. The first agent can also actively ask the user some necessary questions when it manages to disambiguate the vague retrieval requirements. The adaptive defuzzification approach employed in the defuzzifying agent is discussed in detail. A prototype interface has been implemented to demonstrate the effectiveness.

AB - This paper presents a two-agent framework to build a natural language query interface for IC information system, focusing more on scope queries in a single English sentence. The first agent, parsing agent, syntactically processes and semantically interprets natural language sentence to construct a fuzzy structured query language (SQL) statement. The second agent, defuzzifying agent, defuzzifies the imprecise part of the fuzzy SQL statement into its equivalent executable precise SQL statement based on fuzzy rules. The first agent can also actively ask the user some necessary questions when it manages to disambiguate the vague retrieval requirements. The adaptive defuzzification approach employed in the defuzzifying agent is discussed in detail. A prototype interface has been implemented to demonstrate the effectiveness.

KW - Fuzzy rule

KW - Grammar

KW - Integrated circuit information system

KW - Matching degree

KW - Natural language user interface

UR - http://www.scopus.com/inward/record.url?scp=0038823917&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0038823917&partnerID=8YFLogxK

M3 - Article

VL - 4

SP - 152

EP - 161

JO - Journal of Zhejinag University: Science

JF - Journal of Zhejinag University: Science

SN - 1009-3095

IS - 2

ER -