Sökning: "few-shot"

Visar resultat 11 - 15 av 29 uppsatser innehållade ordet few-shot.

1. 11. Automatic generation of definitions : Exploring if GPT is useful for defining words

   Kandidat-uppsats, Linköpings universitet/Institutionen för datavetenskap

   Författare :Fanny Eriksson; [2023]
   Nyckelord :Definitions; NLG; prompt engineering; GPT; GPT-SW3; text-davinci-003;

   Sammanfattning : When reading a text, it is common to get stuck on unfamiliar words that are difficult to understand in the local context. In these cases, we use dictionaries or similar online resources to find the general meaning of the word. LÄS MER

3. 12. Few-shot Question Generation with Prompt-based Learning

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

   Författare :Yongchao Wu; [2022]
   Nyckelord :Nautral Lanugage Processing; Question Generation; Neural Networks; Prompt-based Learning; Language Models;

   Sammanfattning : Question generation (QG), which automatically generates good-quality questions from a piece of text, is capable of lowering the cost of the manual composition of questions. Recently Question generation has attracted increasing interest for its ability to supply a large number of questions for developing conversation systems and educational applications, as well as corpus development for natural language processing (NLP) research tasks, such as question answering and reading comprehension. LÄS MER

4. 13. FEW-SHOT CLASSIFICATION OF EEG WITH QUASI-INDUCTIVE TRANSFER LEARNING

   Kandidat-uppsats, Lunds universitet/Matematisk statistik

   Författare :Mathias Duedahl; [2022]
   Nyckelord :Few-Shot Learning; Transfer Learning; EEG Classification; Deep Convolutional Neural Network; DNN; CNN; EEG; FSL; TL; Mathematics and Statistics;

   Sammanfattning : Brain-computer interfaces (BCIs) are devices that enable people with disabilities to use their thoughts to control external devices and restore or improve their bodily functions. One important aspect of BCIs is the classification of electroencephalography (EEG) signals, which measure brain activity and can be difficult to interpret. LÄS MER

5. 14. Improving a Few-shot Named Entity Recognition Model Using Data Augmentation

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :David Mellin; [2022]
   Nyckelord :Named Entity Recognition; Data Augmentation; Self-training; BERT; Few-shot Learning; Identifiering av namngivna entiteter; Datautökning; Självträning; BERT; Fåförsöksinlärning;

   Sammanfattning : To label words of interest into a predefined set of named entities have traditionally required a large amount of labeled in-domain data. Recently, the availability of pre-trained transformer-based language models have enabled multiple natural language processing problems to utilize transfer learning techniques to construct machine learning models with less task-specific labeled data. LÄS MER

7. 15. A comparative evaluation of machine learning models for engagement classification during presentations : A comparison of distance- and non-distance-based machine learning models for presentation classification and class likelihood estimation

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Rebwar Ali Omer Bajallan; [2022]
   Nyckelord :Audience engagement; Engagement quantification; Machine learning; Distance-based models; Few-shot learning; Statistical analysis; Publiksengagemang; Engagemangskvantifiering; Maskininlärning; Distansbaserade modeller; Few-shot inlärning; Statistisk analys;

   Sammanfattning : In recent years, there has been a significant increase in the usage of audience engagement platforms, which have allowed for engaging interactions between presenters and their audiences. The increased popularity of the platforms comes from the fact that engaging and interactive presentations have been shown to improve learning outcomes and create positive presentation experiences. LÄS MER