Academic Journal
View in EDS
Linked Full Text

Graph NLU enabled question answering system

Bibliographic Details
Title: Graph NLU enabled question answering system
Authors: Sandeep Varma, Shivam Shivam, Snigdha Biswas, Pritam Saha, Khushi Jalan
Source: Heliyon, Vol 7, Iss 9, Pp e08035- (2021)
Publisher Information: Elsevier, 2021.
Publication Year: 2021
Collection: LCC:Science (General)
LCC:Social sciences (General)
Subject Terms: Conversational analytics, Graph traversal, Knowledge graph, Natural language query, Question answering, Structured data, Science (General), Q1-390, Social sciences (General), H1-99
More Details: With a huge amount of information being stored as structured data, there is an increasing need for retrieving exact answers to questions from tables. Answering natural language questions on structured data usually involves semantic parsing of query to a machine understandable format which is then used to retrieve information from the database. Training semantic parsers for domain specific tasks is a tedious job and does not guarantee accurate results. In this paper, we used conversational analytics tool to create the user interface and to get the required entities and intents from the query thus avoiding the traditional semantic parsing approach. We then make use of Knowledge Graph for querying in structured data domain. Knowledge graphs can be easily leveraged for question answering systems, to use them as the database. We extract appropriate answers for different types of queries which have been illustrated in the Results section.
Document Type: article
File Description: electronic resource
Language: English
ISSN: 2405-8440
Relation: http://www.sciencedirect.com/science/article/pii/S2405844021021381; https://doaj.org/toc/2405-8440
DOI: 10.1016/j.heliyon.2021.e08035
Access URL: https://doaj.org/article/9722a51ecffa483d80e884121a5a78e3
Accession Number: edsdoj.9722a51ecffa483d80e884121a5a78e3
Database: Directory of Open Access Journals
FullText Links:
  – Type: other
    Url: https://resolver.ebsco.com:443/public/rma-ftfapi/ejs/direct?AccessToken=4297835002F07212BEC6&Show=Object
Text:
  Availability: 0
CustomLinks:
  – Url: https://www.doi.org/10.1016/j.heliyon.2021.e08035?
    Name: ScienceDirect (all content)-s8985755
    Category: fullText
    Text: View record from ScienceDirect
    MouseOverText: View record from ScienceDirect
  – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsdoj&genre=article&issn=24058440&ISBN=&volume=7&issue=9&date=20210901&spage=&pages=&title=Heliyon&atitle=Graph%20NLU%20enabled%20question%20answering%20system&aulast=Sandeep%20Varma&id=DOI:10.1016/j.heliyon.2021.e08035
    Name: Full Text Finder (for New FTF UI) (s8985755)
    Category: fullText
    Text: Find It @ SCU Libraries
    MouseOverText: Find It @ SCU Libraries
  – Url: https://doaj.org/article/9722a51ecffa483d80e884121a5a78e3
    Name: EDS - DOAJ (s8985755)
    Category: fullText
    Text: View record from DOAJ
    MouseOverText: View record from DOAJ
Header DbId: edsdoj
DbLabel: Directory of Open Access Journals
An: edsdoj.9722a51ecffa483d80e884121a5a78e3
RelevancyScore: 927
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 926.9267578125
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Graph NLU enabled question answering system
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Sandeep+Varma%22">Sandeep Varma</searchLink><br /><searchLink fieldCode="AR" term="%22Shivam+Shivam%22">Shivam Shivam</searchLink><br /><searchLink fieldCode="AR" term="%22Snigdha+Biswas%22">Snigdha Biswas</searchLink><br /><searchLink fieldCode="AR" term="%22Pritam+Saha%22">Pritam Saha</searchLink><br /><searchLink fieldCode="AR" term="%22Khushi+Jalan%22">Khushi Jalan</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Heliyon, Vol 7, Iss 9, Pp e08035- (2021)
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: Elsevier, 2021.
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2021
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: LCC:Science (General)<br />LCC:Social sciences (General)
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Conversational+analytics%22">Conversational analytics</searchLink><br /><searchLink fieldCode="DE" term="%22Graph+traversal%22">Graph traversal</searchLink><br /><searchLink fieldCode="DE" term="%22Knowledge+graph%22">Knowledge graph</searchLink><br /><searchLink fieldCode="DE" term="%22Natural+language+query%22">Natural language query</searchLink><br /><searchLink fieldCode="DE" term="%22Question+answering%22">Question answering</searchLink><br /><searchLink fieldCode="DE" term="%22Structured+data%22">Structured data</searchLink><br /><searchLink fieldCode="DE" term="%22Science+%28General%29%22">Science (General)</searchLink><br /><searchLink fieldCode="DE" term="%22Q1-390%22">Q1-390</searchLink><br /><searchLink fieldCode="DE" term="%22Social+sciences+%28General%29%22">Social sciences (General)</searchLink><br /><searchLink fieldCode="DE" term="%22H1-99%22">H1-99</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: With a huge amount of information being stored as structured data, there is an increasing need for retrieving exact answers to questions from tables. Answering natural language questions on structured data usually involves semantic parsing of query to a machine understandable format which is then used to retrieve information from the database. Training semantic parsers for domain specific tasks is a tedious job and does not guarantee accurate results. In this paper, we used conversational analytics tool to create the user interface and to get the required entities and intents from the query thus avoiding the traditional semantic parsing approach. We then make use of Knowledge Graph for querying in structured data domain. Knowledge graphs can be easily leveraged for question answering systems, to use them as the database. We extract appropriate answers for different types of queries which have been illustrated in the Results section.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: article
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: electronic resource
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 2405-8440
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: http://www.sciencedirect.com/science/article/pii/S2405844021021381; https://doaj.org/toc/2405-8440
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1016/j.heliyon.2021.e08035
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://doaj.org/article/9722a51ecffa483d80e884121a5a78e3" linkWindow="_blank">https://doaj.org/article/9722a51ecffa483d80e884121a5a78e3</link>
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsdoj.9722a51ecffa483d80e884121a5a78e3
PLink https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsdoj&AN=edsdoj.9722a51ecffa483d80e884121a5a78e3
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.heliyon.2021.e08035
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: Conversational analytics
        Type: general
      – SubjectFull: Graph traversal
        Type: general
      – SubjectFull: Knowledge graph
        Type: general
      – SubjectFull: Natural language query
        Type: general
      – SubjectFull: Question answering
        Type: general
      – SubjectFull: Structured data
        Type: general
      – SubjectFull: Science (General)
        Type: general
      – SubjectFull: Q1-390
        Type: general
      – SubjectFull: Social sciences (General)
        Type: general
      – SubjectFull: H1-99
        Type: general
    Titles:
      – TitleFull: Graph NLU enabled question answering system
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Sandeep Varma
      – PersonEntity:
          Name:
            NameFull: Shivam Shivam
      – PersonEntity:
          Name:
            NameFull: Snigdha Biswas
      – PersonEntity:
          Name:
            NameFull: Pritam Saha
      – PersonEntity:
          Name:
            NameFull: Khushi Jalan
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 09
              Type: published
              Y: 2021
          Identifiers:
            – Type: issn-print
              Value: 24058440
          Numbering:
            – Type: volume
              Value: 7
            – Type: issue
              Value: 9
          Titles:
            – TitleFull: Heliyon
              Type: main
ResultId 1