A Modular Neurosymbolic Approach for Visual Graph Question Answering

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Sökning: WFRF:(Higuera Nelson) > A Modular Neurosymb...

LIBRIS Formathandbok (Information om MARC21)

Fältnamn	Indikatorer	Metadata
000		03404naa a2200505 4500
001		oai:DiVA.org:hj-63555
003		SwePub
008		240216s2023 \| \|\|\|\|\|\|\|\|\|\|\|000 \|\|eng\|
024	7	a https://urn.kb.se/resolve?urn=urn:nbn:se:hj:diva-635552 URI
040		a (SwePub)hj
041		a engb eng
042		9 SwePub
072	7	a ref2 swepub-contenttype
072	7	a kon2 swepub-publicationtype
100	1	a Eiter, Thomasu Vienna University of Technology (TU Wien), Vienna, Austria4 aut
245	1 0	a A Modular Neurosymbolic Approach for Visual Graph Question Answering
264	1	b CEUR-WS,c 2023
338		a print2 rdacarrier
520		a Images containing graph-based structures are a ubiquitous and popular form of data representation that, to the best of our knowledge, have not yet been considered in the domain of Visual Question Answering (VQA). We use CLEGR, a graph question answering dataset with a generator that synthetically produces vertex-labelled graphs that are inspired by metro networks. Structured information about stations and lines is provided, and the task is to answer natural language questions concerning such graphs. While symbolic methods suffice to solve this dataset, we consider the more challenging problem of taking images of the graphs instead of their symbolic representations as input. Our solution takes the form of a modular neurosymbolic model that combines the use of optical graph recognition for graph parsing, a pretrained optical character recognition neural network for parsing node labels, and answer-set programming, a popular logic-based approach to declarative problem solving, for reasoning. The implementation of the model achieves an overall average accuracy of 73% on the dataset, providing further evidence of the potential of modular neurosymbolic systems in solving complex VQA tasks, in particular, the use and control of pretrained models in this architecture.
650	7	a NATURVETENSKAPx Data- och informationsvetenskapx Datavetenskap0 (SwePub)102012 hsv//swe
650	7	a NATURAL SCIENCESx Computer and Information Sciencesx Computer Sciences0 (SwePub)102012 hsv//eng
653		a answer-set programming
653		a neurosymbolic computation
653		a visual question answering
653		a Computation theory
653		a Graph theory
653		a Graphic methods
653		a Logic programming
653		a Natural language processing systems
653		a Text processing
653		a Answer set programming
653		a Data representations
653		a Graph-based
653		a Metro networks
653		a Modulars
653		a Question Answering
653		a Vertex-labeled graphs
653		a Visual Graph
653		a Optical character recognition
700	1	a Ruiz, Nelson Higuerau Vienna University of Technology (TU Wien), Vienna, Austria4 aut
700	1	a Oetsch, Johannesu Vienna University of Technology (TU Wien), Vienna, Austria4 aut0 (Swepub:hj)oetjoh
710	2	a Vienna University of Technology (TU Wien), Vienna, Austria4 org
773	0	t Proceedings of the 17th International Workshop on Neural-Symbolic Learning and Reasoning La Certosa di Pontignano, Siena, Italy, July 3-5, 2023d : CEUR-WSg , s. 139-149q <139-149
856	4	u https://ceur-ws.org/Vol-3432/paper11.pdfy Fulltext
856	4 8	u https://urn.kb.se/resolve?urn=urn:nbn:se:hj:diva-63555

Till lärosätets databas

Hitta mer i SwePub

Av författaren/redakt...: Eiter, Thomas; Ruiz, Nelson Hig ...; Oetsch, Johannes

Om ämnet

NATURVETENSKAP: NATURVETENSKAP; och Data och informa ...; och Datavetenskap

Artiklar i publikationen: Proceedings of t ...

Av lärosätet: Jönköping University

Sök utanför SwePub

Sök vidare i:: Google; Google Book Search; Google Scholar

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

LIBRIS.kb.se