Show simple item record

Can grounding the NLI task into a different modality and leveraging existing pre-trained models through zero-shot capabilities improve efficiency and reduce computational demands while maintaining or enhancing task performance?

dc.rights.licenseCC-BY-NC-ND
dc.contributor.advisorPaperno, Denis
dc.contributor.authorSanteer, Ayman
dc.date.accessioned2024-09-12T23:01:58Z
dc.date.available2024-09-12T23:01:58Z
dc.date.issued2024
dc.identifier.urihttps://studenttheses.uu.nl/handle/20.500.12932/47733
dc.description.sponsorshipUtrecht University
dc.language.isoEN
dc.subjectCan grounding the NLI task into a different modality and leveraging existing pre-trained models through zero-shot capabilities improve efficiency and reduce computational demands while maintaining or enhancing task performance?
dc.titleCan grounding the NLI task into a different modality and leveraging existing pre-trained models through zero-shot capabilities improve efficiency and reduce computational demands while maintaining or enhancing task performance?
dc.type.contentMaster Thesis
dc.rights.accessrightsOpen Access
dc.subject.keywordsNLI | Natural Language Inference | Artificial Intelligence | AI
dc.subject.courseuuArtificial Intelligence
dc.thesis.id39292


Files in this item

Thumbnail
Name:
AI_Master_Thesis_2024 copy.pdf
Size:
88.89Mb
Format:
PDF
View/Open

This item appears in the following Collection(s)

Show simple item record