Sökning: "Text Generation"
Visar resultat 16 - 20 av 215 uppsatser innehållade orden Text Generation.
16. muGen : Generative AI as Machinic Exploration of Cultural Archives
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : In recent years, generative AI has quickly become a new creative and artistic tool that could challenge our understanding of the creative process and the role of the machine. Despite having exhibited visually promising results, images generated by AI tools present various challenges, most notably their tendency to display cultural, gender and racial biases. LÄS MER
17. Language Models as Evaluators : A Novel Framework for Automatic Evaluation of News Article Summaries
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The advancements in abstractive summarization using Large Language Models (LLMs) have brought with it new challenges in evaluating the quality and faithfulness of generated summaries. This thesis explores a human-like automated method for evaluating news article summaries. LÄS MER
18. Context-aware Swedish Lexical Simplification : Using pre-trained language models to propose contextually fitting synonyms
Kandidat-uppsats, Linköpings universitet/Institutionen för datavetenskapSammanfattning : This thesis presents the development and evaluation of context-aware Lexical Simplification (LS) systems for the Swedish language. In total three versions of LS models, LäsBERT, LäsBERT-baseline, and LäsGPT, were created and evaluated on a newly constructed Swedish LS evaluation dataset. LÄS MER
19. Towards Building Privacy-Preserving Language Models: Challenges and Insights in Adapting PrivGAN for Generation of Synthetic Clinical Text
Master-uppsats, Stockholms universitet/Institutionen för data- och systemvetenskapSammanfattning : The growing development of artificial intelligence (AI), particularly neural networks, is transforming applications of AI in healthcare, yet it raises significant privacy concerns due to potential data leakage. As neural networks memorise training data, they may inadvertently expose sensitive clinical data to privacy breaches, which can engender serious repercussions like identity theft, fraud, and harmful medical errors. LÄS MER
20. Hur äldre internetanvändare lättare kan förstå hur man använder 1177.se : Att förnya recept med hjälp av 1177:s e-tjänster
Kandidat-uppsats, Mälardalens universitet/Akademin för innovation, design och teknikSammanfattning : Det är ofta äldre personer behöver besöka 1177.se och på grund av att samhället och dess information har blivit alltmer digitaliserad blir det svårare för den äldre generationen som inte växt upp med den nu moderna tekniken. LÄS MER