Sökning: "fine tuning"

Visar resultat 16 - 20 av 226 uppsatser innehållade orden fine tuning.

  1. 16. Round-Trip Translation : A New Path for Automatic Program Repair using Large Language Models

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

    Författare :Fernando Vallecillos Ruiz; [2023]
    Nyckelord :Automatic Program Repair; Software Engineering; Large Language Models; Round-Trip Translation; Neural Machine Translation; Automatisk programreparation; Mjukvaruutveckling; Stora språkmodeller; Tur och retur-översättning; Neural maskinöversättning;

    Sammanfattning : Research shows that grammatical mistakes in a sentence can be corrected by machine translating it to another language and back. We investigate whether this correction capability of Large Language Models (LLMs) extends to Automatic Program Repair (APR), a software engineering task. LÄS MER

  3. 17. Automated Interpretation of Lung Ultrasound for COVID-19 and Tuberculosis diagnosis

    Master-uppsats, Lunds universitet/Matematik LTH

    Författare :Chloé Soormally; [2023]
    Nyckelord :Tuberculosis; COVID-19; Lung Ultrasound; Computer-aided detection CAD ; Deep learning; Technology and Engineering;

    Sammanfattning : BACKGROUND. Early and accurate detection of infectious respiratory diseases like COVID-19 and tuberculosis (TB) plays a crucial role in effective management and the reduction of preventable mortality. LÄS MER

  4. 18. Fine-tuning a BERT-based NER Model for Positive Energy Districts

    Master-uppsats, Högskolan Dalarna/Institutionen för information och teknik

    Författare :Karen Ortega; Fei Sun; [2023]
    Nyckelord :Positive Energy District PED ; Named Entity Recognition NER ; Bidirectional Encoder Representations from Transformers BERT ; Pipeline; Fine-tune;

    Sammanfattning : This research presents an innovative approach to extracting information from Positive Energy Districts (PEDs), urban areas generating surplus energy. PEDs are integral to the European Commission's SET Plan, tackling housing challenges arising from population growth. LÄS MER

  5. 19. Context-aware Swedish Lexical Simplification : Using pre-trained language models to propose contextually fitting synonyms

    Kandidat-uppsats, Linköpings universitet/Institutionen för datavetenskap

    Författare :Emil Graichen; [2023]
    Nyckelord :automatic text simplification; lexical simplification; Swedish; BERT; GPT-3; evaluation dataset; synonymy;

    Sammanfattning : 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

  7. 20. The Impact of the Retrieval Text Set for Text Sentiment Classification With the Retrieval-Augmented Language Model REALM

    Master-uppsats, KTH/Matematik (Inst.)

    Författare :Oscar Blommegård; [2023]
    Nyckelord :The Impact of the Retrieval Text Set for Text Sentiment Classification With the Retrieval-Augmented Language Model REALM; Hämtningsförstärkta språkmodeller; Natural Language Processing; Transformers; Djupinlärning; Textklassificering;

    Sammanfattning : Large Language Models (LLMs) have demonstrated impressive results across various language technology tasks. By training on large corpora of diverse text collections from the internet, these models learn to process text effectively, allowing them to acquire comprehensive world knowledge. LÄS MER