uu.seUppsala University Publications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • 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
Deeplurn: Learning meaning from a game environment using deep learning methods
Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Languages, Department of Linguistics and Philology.
2017 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

A long-standing goal of Artificial Intelligence is to enable natural communication between machines and humans. Dialogue, arguably the most common form of human expression, remains difficult for machines to navigate. In this work we focus on the emergence of meaning in goal-based dialogue between human and machine, and how best to develop it using deep learning methods.

We evaluate this emergence in a virtual command-action game, where a machine with no prior knowledge deciphers the user's natural language command to move coloured blocks.On a fundamental level this moves us closer to an understanding and synthesis of natural meaning creation. On an applied level, this method has the potential to reduce reliance on large corpora of annotated language, in the hopes that future natural language understanding will be tailored to the individual user, irrespective of language-specific resources.

Place, publisher, year, edition, pages
2017.
Keywords [en]
machine learning, deep learning, nlp
National Category
Language Technology (Computational Linguistics)
Identifiers
URN: urn:nbn:se:uu:diva-339976OAI: oai:DiVA.org:uu-339976DiVA, id: diva2:1177266
External cooperation
Microsoft Research Ltd.
Supervisors
Examiners
Available from: 2018-01-30 Created: 2018-01-24 Last updated: 2018-01-30Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
Department of Linguistics and Philology
Language Technology (Computational Linguistics)

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 129 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • 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