20.500.12556/DKUM-78108 Klasifikacija besedila s prenosnim učenjem magistrsko delo Classification of text using transfer learning Magistrsko delo ima namen preizkusiti metodo prenosnega učenja na obdelavi naravnega jezika in jo primerjati s klasičnimi metodami učenja nevronskih mrež, metodo LSTM. V delu sta uporabljena opisna metoda za teoretični in eksperiment za praktični del dela. V slednjem smo ugotovili, da je metoda prenosnega učenja na majhni količini podatkov bolj točna od klasičnih metod, vendar za to potrebuje več časa. Delo primerja prednaučeni model Bert in klasično metodo LSTM, zato je priporočljivo primerjati rezultate tudi z drugimi prednaučenimi modeli in klasičnimi metodami. The aim of this Master's thesis is to test the method of transfer learning with natural language processing and to compare it to a standard neural network model, namely LSTM. The thesis is using the descriptive method for the theoretical part and experimental method for the practical part. In the experiment we have discovered that, while transfer learning is more accurate than the standard model, it is also slower in the learning process. The thesis compares only the pretrained model Bert and standard model LSTM and that is why it is recommended to also check other pretrained models and standard models for comparison. nevronske mreže prenosno učenje NLP PyTorch LSTM neural networks transfer learning NLP PyTorch LSTM true true false [J. Žerak] Slovenski jezik Angleški jezik Magistrsko delo/naloga 2020-10-27 08:51:15 2020-12-01 13:31:44 2022-08-09 17:35:20 2020-12-25 03:22:13 2020 0 Maribor 0 Maribor IX, 64 f. 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.85(043.2) 44103683 URN:SI:UM:DK:VRY2V0LQ MAG_Zerak_Jure_2020.pdf MAG_Zerak_Jure_2020.pdf 1 7C9C0FF29C1B8078C99A4AF3BC808FF8 43b0384796c86c06d21bca3ffaaec83a614b386ebf2ef66778fc0e983fcabb0d 0586a1fc-7c12-11eb-bb7a-00155d0001ca 20.500.12556/dkum/f31311e4-f917-41e0-8bdd-03fcc3752859 https://dk.um.si/Dokument.php?lang=slv&id=147764 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0