Digitala Vetenskapliga Arkivet

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
Question generation for language café interaction between robot and human: NLP applied in a robot
KTH, School of Electrical Engineering and Computer Science (EECS).
KTH, School of Electrical Engineering and Computer Science (EECS).
2019 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

Conversational robots can be used in several contexts, one of them being language cafés. This setting demands that the robot in question can converse on many different subjects and move between them smoothly. For this to be possible one needs to generate many questions on a range of subjects and find a way of moving from one subject to another. This work aims to do this by generating questions using a template framework and navigating between them using clustering, a scalable solution which is adapted to language café settings. The general value of language cafés and their role in a language learning process is also discussed.

Abstract [sv]

 Konversationsrobotar kan användas i många olika miljöer, där en av dem är språkcaféer. Denna miljö ställer krav på roboten att den kan föra ett samtal kring många olika ämnen och även byta ämne smidigt. För att kunna göra detta behöver man generera många frågor som handlar om många olika ämnen och även hitta ett sätt att byta från ett ämnne till ett annat. Detta arbete ämnar göra detta genom att använda ett mall-ramverk för att generera frågor och klustring för att navigera mellan dem, en skalbar lösning som är anpassad för språkcafémiljöer. Det generella värdet av språkcaféer och deras roll i en språkinlärningsprocess diskuteras också.

Place, publisher, year, edition, pages
2019. , p. 12
Series
TRITA-EECS-EX ; 2019:437
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-259555OAI: oai:DiVA.org:kth-259555DiVA, id: diva2:1352132
Supervisors
Examiners
Available from: 2019-10-02 Created: 2019-09-17 Last updated: 2022-06-26Bibliographically approved

Open Access in DiVA

fulltext(7729 kB)468 downloads
File information
File name FULLTEXT01.pdfFile size 7729 kBChecksum SHA-512
78e78e3ef62273ab7e66b862b3c0c03f6fb937206f952ffc30172891412c57d7e45275a989da81bd021b8843952cff05599f661c27f4cdb9dd6deb7c6f1a5001
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 468 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: 372 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