To Örebro University

oru.seÖrebro University Publications
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
Compositional Generalization and Neuro-Symbolic Architectures
Örebro University, School of Science and Technology. (AASS)ORCID iD: 0000-0003-3902-2867
Örebro University, School of Science and Technology. (AASS)ORCID iD: 0000-0002-4001-2087
2022 (English)In: AAAI - Combining Learning and Reasoning: Programming Languages, Formalisms, and Representations, CLeaR 2022, 2022Conference paper, Published paper (Refereed)
Abstract [en]

Compositional generalization is the ability to understand novel combinations of known concepts. Although it is considered as an innate skill for humans, recent studies have shown that neural networks lack this characteristic. In this paper, we focus on compositional generalization with respect to the two specific tasks of word problem solving and visual relation recognition and propose a neuro-symbolic solution, using DeepProbLog, that addresses the problem of compositionality in state-of-the-art neural systems for these tasks.

Place, publisher, year, edition, pages
2022.
Keywords [en]
Compositional generalization, Neuro-symbolic AI, DeepProbLog, Word Problem Solving, Visual Relation Recognition
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:oru:diva-96878OAI: oai:DiVA.org:oru-96878DiVA, id: diva2:1633254
Conference
36th AAAI conference on artificial intelligence (AAAI-2022), Vancouver, BC, Canada, February 22 - March 1, 2022
Available from: 2022-01-28 Created: 2022-01-28 Last updated: 2022-03-31Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Free full text

Authority records

Sam Abraham, SavithaAlirezaie, Marjan

Search in DiVA

By author/editor
Sam Abraham, SavithaAlirezaie, Marjan
By organisation
School of Science and Technology
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 1835 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