Sökning: "T5"
Visar resultat 1 - 5 av 33 uppsatser innehållade ordet T5.
1. Where to Fuse
Master-uppsats, Lunds universitet/Matematisk statistikSammanfattning : This thesis investigates fusion techniques in multimodal transformer models, focusing on enhancing the capabilities of large language models in understanding not just text, but also other modalities like images, audio, and sensor data. The study compares late fusion (concatenating modality tokens after separate encoding) and early fusion (concatenating before encoding) techniques, examining their respective advantages and disadvantages. LÄS MER
2. Automatic Semantic Role Labelling (SRL) in Swedish
Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknikSammanfattning : In this paper, using deep learning networks, the first end-to-end semantic role labelling model (SRL) has been developed for Swedish texts. This Swedish SRL model can, with a given Swedish sentence, perform trigger identification, frame classification and argument extraction tasks automatically in a series. LÄS MER
3. Text to Music Audio Generation using Latent Diffusion Model : A re-engineering of AudioLDM Model
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : In the emerging field of audio generation using diffusion models, this project pioneers the adaptation of the AudioLDM model framework, initially designed for text-to-daily sounds generation, towards text-to-music audio generation. This shift addresses a gap in the current scope of audio diffusion models, predominantly focused on everyday sounds. LÄS MER
4. AI-sammanfattade klagomål på hälso- och sjukvård
Kandidat-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknikSammanfattning : Detta examensarbete utfördes i samarbete med Patientnämnden Skåne, som är en av Region Skånes fristående förvaltningar. Patientnämnden ansvarar bland annat för hantering av patienters klagomål om hälso- och sjukvård som tillhör Region Skåne. Att sammanfatta klagomål är en av uppgifterna inom hanteringen av klagomål. LÄS MER
5. Prompt-learning and Zero-shot Text Classification with Domain-specific Textual Data
Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologiSammanfattning : The rapid growth of textual data in the digital age presents unique challenges in domain-specific text classification, particularly the scarcity of labeled data for many applications, due to expensive cost of manual labeling work. In this thesis, we explore the applicability of prompt-learning method, which is well-known for being suitable in few-shot scenarios and much less data-consuming, as an emerging alternative to traditional fine-tuning methods, for domain-specific text classification in the context of customer-agent interactions in the retail sector. LÄS MER