Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Context modeling using a common sensedatabase
KTH, School of Computer Science and Communication (CSC).
KTH, School of Computer Science and Communication (CSC).
2013 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

Common sense databases are collections of human common

sense knowledge. With these databases available, a lot of

possibilities arise regarding understanding human language

and putting it into a context. This essay aims to discuss

how a common sense database could be used to enable a

more human-like grasp of context in conversational agents.

To try out the possibilities of context modeling using these

databases we built a prototype that uses the knowledge base

ConceptNet. Our tests showed that there are some issues

with ConceptNet for our purposes regarding the quality of

the data. However, we were still able to find some interesting

previous research in the area, and were able to get

some useful results using our prototype.

Abstract [sv]

”Common sense”-databaser är samlingar av mänskligt sunt

förnuft. Med dessa databaser dyker det upp en hel del möjligheter

gällande förståelse av mänskligt språk och förmågan

att sätta det i en kontext. Denna uppsats syftar till att

diskutera hur en “common sense”-databas kan användas för

att ge ett dialogsystem mer mänsklig uppfattning av kontext.

För att testa möjligheterna med kontextmodellering

med hjälp av dessa databaser byggde vi en prototyp som

använder databasen ConceptNet. Våra tester visade att det

finns vissa problem med att uppnå våra mål med hjälp av

ConceptNet på grund av bristande kvalitet på viss data.

Det finns däremot mycket mer att utforska och vi fann intressant

forskning på området, samt fick en del användbara

resultat med vår prototyp.

Place, publisher, year, edition, pages
2013.
Series
Kandidatexjobb CSC, K13034
National Category
Computer Science
Identifiers
URN: urn:nbn:se:kth:diva-134951OAI: oai:DiVA.org:kth-134951DiVA: diva2:668859
Educational program
Master of Science in Engineering - Computer Science and Technology
Supervisors
Examiners
Available from: 2013-12-13 Created: 2013-12-02 Last updated: 2013-12-13Bibliographically approved

Open Access in DiVA

Context modeling using a common sense(590 kB)165 downloads
File information
File name FULLTEXT01.pdfFile size 590 kBChecksum SHA-512
884be2202a4ef42c39e2f690a7738a9061009bd45f687144d48fc7f48bb2fed2acaaefc89c65f02560de9606923cd8a1de60a051ac9feeeae598eeed7331d82b
Type fulltextMimetype application/pdf

Other links

http://www.csc.kth.se/utbildning/kth/kurser/DD143X/dkand13/Group6Gabriel/report/report_gustaf_martin.pdf
By organisation
School of Computer Science and Communication (CSC)
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 165 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 56 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf