IMPLEMENTING PERCEPTUAL SEMANTICS IN TYPE THEORY WITH RECORDS (TTR)

dc.contributor.author	Matsson, Arild
dc.contributor.department	University of Gothenburg / Department of Philosophy,Lingustics and Theory of Science	eng
dc.contributor.department	Göteborgs universitet / Institutionen för filosofi, lingvistik och vetenskapsteori	swe
dc.date.accessioned	2019-11-18T12:53:24Z
dc.date.available	2019-11-18T12:53:24Z
dc.date.issued	2019-11-18
dc.description.abstract	Type Theory with Records (TTR) provides accounts of a wide range of semantic and linguistic phenomena in a single framework. This work proposes a TTR model of perception and language. Utilizing PyTTR, a Python implementation of TTR, the model is then implemented as an executable script. Over pure Python programming, TTR provides a transparent formal specification. The implementation is evaluated in a basic visual question answering (VQA) use case scenario. The results show that an implementation of a TTR model can account for multi-modal knowledge representation and work in a VQA setting.	sv
dc.identifier.uri	http://hdl.handle.net/2077/62521
dc.language.iso	eng	sv
dc.setspec.uppsok	HumanitiesTheology
dc.subject	visual question answering	sv
dc.subject	artificial intelligence	sv
dc.subject	type theory	sv
dc.subject	image recognition	sv
dc.subject	perceptual semantics	sv
dc.subject	spatial relations	sv
dc.title	IMPLEMENTING PERCEPTUAL SEMANTICS IN TYPE THEORY WITH RECORDS (TTR)	sv
dc.type	Text
dc.type.degree	Student essay
dc.type.uppsok	H2

Files

Now showing 1 - 1 of 1

Now showing 1 - 1 of 1