Gurmukhi Punjabi (PA) as a low resource-language through the lens of the BLARK model.

dc.contributor.authorKaur, Kirandeep
dc.contributor.supervisorO'Donnell, Daniel Paul
dc.contributor.supervisorSnoek, Conor
dc.date.accessioned2023-09-08T21:28:39Z
dc.date.available2023-09-08T21:28:39Z
dc.date.issued2023
dc.degree.levelMasters
dc.description.abstractWe are venturing into the next phase of digital divide (unequal access to digital technology), where the languages which are not ready for Natural Language Processing (NLP) are at the most risk of losing out on the developments in the fields of Speech and Language technologies. This has brought forth a big gap between the readiness of different languages in terms of taking advantage of the recent developments in the field of computational technologies. Common Language Resources and Technology Infrastructure (CLARIN) - a large-scale pan-European collaborative effort to create, coordinate and make language resources and technology available and readily usable, has developed the Basic Language Resource Kit (BLARK) model to assess the readiness for speech and language technology developments in any language. Punjabi, despite being a major language with millions of native speakers and a significant diaspora population around the world, has received limited attention in the computational technologies. The thesis aims to provide a comprehensive overview of the existing resources, tools, and techniques for Punjabi NLP, as well as to identify the gaps and opportunities for future research using BLARK model as a framework. The thesis, after giving the current (sorry) state of Punjabi in terms of its readiness for computation technologies, concludes with some suggestions for directions and effort which are needed for making Punjabi ready for development of speech and language technologies. The thesis contributes to the field of Punjabi language processing by proposing a generic model for comparing and enhancing Punjabi linguistic resources.
dc.identifier.urihttps://hdl.handle.net/10133/6583
dc.language.isoen
dc.proquest.subject0290
dc.proquest.subject0800
dc.proquest.subject0984
dc.proquest.subject0291
dc.proquestyesYes
dc.publisherLethbridge, Alta. : University of Lethbridge, Dept. of English
dc.publisher.departmentDepartment of English
dc.publisher.facultyArts and Science
dc.relation.ispartofseriesThesis (University of Lethbridge. Faculty of Arts and Science)
dc.subjectPunjabi language
dc.subjectGurmukhi
dc.subjectLow-resource language
dc.subjectBLARK model
dc.subjectBasic Language Resource kit
dc.subjectComputational technology
dc.subjectLanguage processing
dc.subjectSpeech technologies
dc.subjectLanguage technologies
dc.subject.lcshPanjabi language
dc.subject.lcshLow-resource languages
dc.subject.lcshNatural language processing (Computer science)
dc.subject.lcshComputational linguistics
dc.subject.lcshDissertations, Academic
dc.titleGurmukhi Punjabi (PA) as a low resource-language through the lens of the BLARK model.
dc.typeThesis
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
KAUR_KIRANDEEP_MA_2023.pdf
Size:
4.86 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
3.25 KB
Format:
Item-specific license agreed upon to submission
Description: