PNL-Enhanced Restricted Domain Question Answering System

The concept of PNL (Precisiated Natural Language) has been proposed by Zadeh for computation with perceptions and some problems described in natural language. We describe a design for restricted domain question answering systems enhanced by PNL-based reasoning. For a subset of a knowledge corpus (e....

Full description

Saved in:
Bibliographic Details
Main Authors: Sufyan Beg, M.M., Thint, M., Zengchang Qin
Format: Conference Proceeding
Language:English
Subjects:
Application software
Computational intelligence
Data mining
Fellows
Fuzzy sets
Humans
Natural languages
Ontologies
Search engines
Telecommunication computing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 7
container_issue
container_start_page 1
container_title
container_volume
creator Sufyan Beg, M.M.
Thint, M.
Zengchang Qin
description The concept of PNL (Precisiated Natural Language) has been proposed by Zadeh for computation with perceptions and some problems described in natural language. We describe a design for restricted domain question answering systems enhanced by PNL-based reasoning. For a subset of a knowledge corpus (e.g. critical or frequently-asked topics) where fuzzy set definitions of vague terms are provided, more precise answers can be computed via protoformal deduction. Nested structure in the system design also enables processing of natural language statements that are not PNL protoforms using phrase-based deduction and concept matching to generate the most relevant facts for a query. If deduction results yield low confidence factor, standard search engine provides a baseline response (relevant paragraphs based on keyword matches). Our design principles aim for flexible, domain independent capability and minimize human input to provision of semantic clues and background knowledge during design or application set-up.
doi_str_mv 10.1109/FUZZY.2007.4295551
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4295551</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4295551</ieee_id><sourcerecordid>4295551</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-a33aa6965e3cc3f999136aaeada78fc178eb3a9cb32e2bb58448a4da89483b9b3</originalsourceid><addsrcrecordid>eNotT8tOwzAQNAIkSskPwCU_kOBn7D1WpQWkiGc50Eu1dhwwIi6Kg6r-PZHoXOYh7WqGkEtGS8YoXC_f1uv3klOqS8lBKcWOSAbaMMmlZJxRdUzOD4YCnJDJeGUKrYw8I1lKX3QESCaVnhDz9FAXi_iJ0fkmf_Fp6IMbRnmz7TDE_Pl3jMI25rOYdr4P8SN_3afBdxfktMXv5LMDT8lquVjN74r68fZ-PquLAHQoUAjECirlhXOiBQAmKkSPDWrTOqaNtwLBWcE9t3asKA3KBg1IIyxYMSVX_2-D937z04cO-_3msFv8AUVeSfc</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>PNL-Enhanced Restricted Domain Question Answering System</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Sufyan Beg, M.M. ; Thint, M. ; Zengchang Qin</creator><creatorcontrib>Sufyan Beg, M.M. ; Thint, M. ; Zengchang Qin</creatorcontrib><description>The concept of PNL (Precisiated Natural Language) has been proposed by Zadeh for computation with perceptions and some problems described in natural language. We describe a design for restricted domain question answering systems enhanced by PNL-based reasoning. For a subset of a knowledge corpus (e.g. critical or frequently-asked topics) where fuzzy set definitions of vague terms are provided, more precise answers can be computed via protoformal deduction. Nested structure in the system design also enables processing of natural language statements that are not PNL protoforms using phrase-based deduction and concept matching to generate the most relevant facts for a query. If deduction results yield low confidence factor, standard search engine provides a baseline response (relevant paragraphs based on keyword matches). Our design principles aim for flexible, domain independent capability and minimize human input to provision of semantic clues and background knowledge during design or application set-up.</description><identifier>ISSN: 1098-7584</identifier><identifier>ISBN: 1424412099</identifier><identifier>ISBN: 9781424412099</identifier><identifier>EISBN: 9781424412105</identifier><identifier>EISBN: 1424412102</identifier><identifier>DOI: 10.1109/FUZZY.2007.4295551</identifier><language>eng</language><publisher>IEEE</publisher><subject>Application software ; Computational intelligence ; Data mining ; Fellows ; Fuzzy sets ; Humans ; Natural languages ; Ontologies ; Search engines ; Telecommunication computing</subject><ispartof>2007 IEEE International Fuzzy Systems Conference, 2007, p.1-7</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4295551$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,27901,54894</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4295551$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Sufyan Beg, M.M.</creatorcontrib><creatorcontrib>Thint, M.</creatorcontrib><creatorcontrib>Zengchang Qin</creatorcontrib><title>PNL-Enhanced Restricted Domain Question Answering System</title><title>2007 IEEE International Fuzzy Systems Conference</title><addtitle>FUZZY</addtitle><description>The concept of PNL (Precisiated Natural Language) has been proposed by Zadeh for computation with perceptions and some problems described in natural language. We describe a design for restricted domain question answering systems enhanced by PNL-based reasoning. For a subset of a knowledge corpus (e.g. critical or frequently-asked topics) where fuzzy set definitions of vague terms are provided, more precise answers can be computed via protoformal deduction. Nested structure in the system design also enables processing of natural language statements that are not PNL protoforms using phrase-based deduction and concept matching to generate the most relevant facts for a query. If deduction results yield low confidence factor, standard search engine provides a baseline response (relevant paragraphs based on keyword matches). Our design principles aim for flexible, domain independent capability and minimize human input to provision of semantic clues and background knowledge during design or application set-up.</description><subject>Application software</subject><subject>Computational intelligence</subject><subject>Data mining</subject><subject>Fellows</subject><subject>Fuzzy sets</subject><subject>Humans</subject><subject>Natural languages</subject><subject>Ontologies</subject><subject>Search engines</subject><subject>Telecommunication computing</subject><issn>1098-7584</issn><isbn>1424412099</isbn><isbn>9781424412099</isbn><isbn>9781424412105</isbn><isbn>1424412102</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2007</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotT8tOwzAQNAIkSskPwCU_kOBn7D1WpQWkiGc50Eu1dhwwIi6Kg6r-PZHoXOYh7WqGkEtGS8YoXC_f1uv3klOqS8lBKcWOSAbaMMmlZJxRdUzOD4YCnJDJeGUKrYw8I1lKX3QESCaVnhDz9FAXi_iJ0fkmf_Fp6IMbRnmz7TDE_Pl3jMI25rOYdr4P8SN_3afBdxfktMXv5LMDT8lquVjN74r68fZ-PquLAHQoUAjECirlhXOiBQAmKkSPDWrTOqaNtwLBWcE9t3asKA3KBg1IIyxYMSVX_2-D937z04cO-_3msFv8AUVeSfc</recordid><startdate>200706</startdate><enddate>200706</enddate><creator>Sufyan Beg, M.M.</creator><creator>Thint, M.</creator><creator>Zengchang Qin</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>200706</creationdate><title>PNL-Enhanced Restricted Domain Question Answering System</title><author>Sufyan Beg, M.M. ; Thint, M. ; Zengchang Qin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-a33aa6965e3cc3f999136aaeada78fc178eb3a9cb32e2bb58448a4da89483b9b3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2007</creationdate><topic>Application software</topic><topic>Computational intelligence</topic><topic>Data mining</topic><topic>Fellows</topic><topic>Fuzzy sets</topic><topic>Humans</topic><topic>Natural languages</topic><topic>Ontologies</topic><topic>Search engines</topic><topic>Telecommunication computing</topic><toplevel>online_resources</toplevel><creatorcontrib>Sufyan Beg, M.M.</creatorcontrib><creatorcontrib>Thint, M.</creatorcontrib><creatorcontrib>Zengchang Qin</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library Online</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Sufyan Beg, M.M.</au><au>Thint, M.</au><au>Zengchang Qin</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>PNL-Enhanced Restricted Domain Question Answering System</atitle><btitle>2007 IEEE International Fuzzy Systems Conference</btitle><stitle>FUZZY</stitle><date>2007-06</date><risdate>2007</risdate><spage>1</spage><epage>7</epage><pages>1-7</pages><issn>1098-7584</issn><isbn>1424412099</isbn><isbn>9781424412099</isbn><eisbn>9781424412105</eisbn><eisbn>1424412102</eisbn><abstract>The concept of PNL (Precisiated Natural Language) has been proposed by Zadeh for computation with perceptions and some problems described in natural language. We describe a design for restricted domain question answering systems enhanced by PNL-based reasoning. For a subset of a knowledge corpus (e.g. critical or frequently-asked topics) where fuzzy set definitions of vague terms are provided, more precise answers can be computed via protoformal deduction. Nested structure in the system design also enables processing of natural language statements that are not PNL protoforms using phrase-based deduction and concept matching to generate the most relevant facts for a query. If deduction results yield low confidence factor, standard search engine provides a baseline response (relevant paragraphs based on keyword matches). Our design principles aim for flexible, domain independent capability and minimize human input to provision of semantic clues and background knowledge during design or application set-up.</abstract><pub>IEEE</pub><doi>10.1109/FUZZY.2007.4295551</doi><tpages>7</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1098-7584
ispartof 2007 IEEE International Fuzzy Systems Conference, 2007, p.1-7
issn 1098-7584
language eng
recordid cdi_ieee_primary_4295551
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Application software
Computational intelligence
Data mining
Fellows
Fuzzy sets
Humans
Natural languages
Ontologies
Search engines
Telecommunication computing
title PNL-Enhanced Restricted Domain Question Answering System
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-24T17%3A30%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=PNL-Enhanced%20Restricted%20Domain%20Question%20Answering%20System&rft.btitle=2007%20IEEE%20International%20Fuzzy%20Systems%20Conference&rft.au=Sufyan%20Beg,%20M.M.&rft.date=2007-06&rft.spage=1&rft.epage=7&rft.pages=1-7&rft.issn=1098-7584&rft.isbn=1424412099&rft.isbn_list=9781424412099&rft_id=info:doi/10.1109/FUZZY.2007.4295551&rft.eisbn=9781424412105&rft.eisbn_list=1424412102&rft_dat=%3Cieee_6IE%3E4295551%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i90t-a33aa6965e3cc3f999136aaeada78fc178eb3a9cb32e2bb58448a4da89483b9b3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4295551&rfr_iscdi=true