Sökning: "transformer models"

Visar resultat 21 - 25 av 209 uppsatser innehållade orden transformer models.

1. 21. Head-to-head Transfer Learning Comparisons made Possible : A Comparative Study of Transfer Learning Methods for Neural Machine Translation of the Baltic Languages

   Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

   Författare :Mathias Stenlund; [2023]
   Nyckelord :machine translation; transfer learning; Latvian; Lithuanian; low-resource languages; transformers; parent language; child language; comparative study;

   Sammanfattning : The struggle of training adequate MT models using data-hungry NMT frameworks for low-resource language pairs has created a need to alleviate the scarcity of sufficiently large parallel corpora. Different transfer learning methods have been introduced as possible solutions to this problem, where a new model for a target task is initialized using parameters learned from some other high-resource task. LÄS MER

3. 22. Punctuation Restoration as Post-processing Step for Swedish Language Automatic Speech Recognition

   Magister-uppsats, Luleå tekniska universitet/Institutionen för system- och rymdteknik

   Författare :Ishika Gupta; [2023]
   Nyckelord :Transformer; BERT; KB-BERT; NLP; punctuation restoration; deep learning; neural networks;

   Sammanfattning : This thesis focuses on the Swedish language, where punctuation restoration, especially as a postprocessing step for the output of Automatic Speech Recognition (ASR) applications, needs furtherresearch. I have collaborated with NewsMachine AB, a company that provides large-scale mediamonitoring services for its clients, for which it employs ASR technology to convert spoken contentinto text. LÄS MER

4. 23. Metod för ett automatiserat frågebesvarande i det svenska språket

   M1-uppsats, KTH/Hälsoinformatik och logistik

   Författare :Kristian Penna; [2023]
   Nyckelord :question answering; natural language processing; artificial intelligence; machine learning; deep learning; artificial neural networks; transformer; BERT; sentence transformers; semantic textual similarity; frågebesvarande; språkteknologi; artificiell intelligens; maskininlärning; djupinlärning; artificiella neurala nätverk; transformer; BERT; sentence transformers; semantisk textlikhet;

   Sammanfattning : I ärendehanteringssystem utgör avslutade ärenden en värdefull datamängd bestående av par av frågor och svar som organisationer med rätt metoder kan dra nytta av för att utvinna fördelar. I denna studie har en Sentence Transformers-modell blivit finjusterad för question answering som tillsammans med en datamängd från ett ärendehanteringssystem automatiskt kan besvara organisationsspecifika frågor i det svenska språket. LÄS MER

5. 24. Evaluation of deep learning methods for industrial automation

   Master-uppsats, Umeå universitet/Institutionen för datavetenskap

   Författare :Ragnar Onning; [2023]
   Nyckelord :artificial intelligence; machine learning; deep learning; cnn; transformer; swin; swin transformer;

   Sammanfattning : The rise and adaptation of the transformer architecture from natural language processing to visual tasks have proven a useful and powerful tool. Subsequent architectures such as visual transformers (ViT) and shifting window (SWIN) transformers have proven to be comparable and oftentimes exceed convolutional neural networks (CNNs) in terms of accuracy. LÄS MER

7. 25. Predicting the Unpredictable – Using Language Models to Assess Literary Quality

   Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

   Författare :Yaru Wu; [2023]
   Nyckelord :perplexity; variance; unpredictability; homogeneity; generative pre-trained models; text generation; literary quality;

   Sammanfattning : People read for various purposes like learning specific skills, acquiring foreign languages, and enjoying the pure reading experience, etc. This kind of pure enjoyment may credit to many aspects, such as the aesthetics of languages, the beauty of rhyme, and the entertainment of being surprised by what will happen next, the last of which is typically featured in fictional narratives and is also the main topic of this project. LÄS MER