Sökning: "Behandling av naturliga språk"

Visar resultat 1 - 5 av 7 uppsatser innehållade orden Behandling av naturliga språk.

  1. 1. A Prompting Framework for Natural Language Processing in the Medical Field : Assessing the Potential of Large Language Models for Swedish Healthcare

    Master-uppsats, KTH/Medicinteknik och hälsosystem

    Författare :Anim Mondal; [2023]
    Nyckelord :Healthcare; NLP; GPT; framework; medical; AI; Hälsovård; NLP; GPT; ramverk; medicin; AI;

    Sammanfattning : The increasing digitisation of healthcare through the use of technology and artificial intelligence has affected the medical field in a multitude of ways. Generative Pre-trained Transformers (GPTs) is a collection of language models that have been trained on an extensive data set to generate human-like text and have been shown to achieve a strong understanding of natural language. LÄS MER

  3. 2. Compressing Deep Learning models for Natural Language Understanding

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

    Författare :Nadir Ait Lahmouch; [2022]
    Nyckelord :Natural Language Processing; Deep learning; BERT; Knowledge Distillation; Pruning.;

    Sammanfattning : Uppgifter för behandling av naturliga språk (NLP) har under de senaste åren visat sig vara särskilt effektiva när man använder förtränade språkmodeller som BERT. Det enorma kravet på datorresurser som krävs för att träna sådana modeller gör det dock svårt att använda dem i verkligheten. LÄS MER

  4. 3. Extracting information about arms deals from news articles

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

    Författare :Fredrik Hernqvist; [2022]
    Nyckelord :Natural Language Processing; Machine Learning; Deep Learning; BERT; ALBERT; Arms Transfers; Information Extraction; Behandling av naturliga språk; maskininlärning; djupinlärning; BERT; ALBERT; vapenaffärer;

    Sammanfattning : The Stockholm International Peace Research Institute (SIPRI) maintains the most comprehensive publicly available database on international arms deals. Updating this database requires humans to sift through large amounts of news articles, only some of which contain information relevant to the database. LÄS MER

  5. 4. Evaluation of the performance of machine learning techniques for email classification

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

    Författare :Isabella Tapper; [2022]
    Nyckelord :Natural Language Processing; Text Representations; Email Classification; Text Classification; Behandling Av Naturliga Språk; Text Representation; epost-klassificering; Textklassificering;

    Sammanfattning : Manual categorization of a mail inbox can often become time-consuming. Therefore many attempts have been made to use machine learning for this task. One essential Natural Language Processing (NLP) task is text classification, which is a big challenge since an NLP engine is not a native speaker of any human language. LÄS MER

  7. 5. BERT Language Modelling on Network Log Data for Generalized Unsupervised Intrusion Detection

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

    Författare :Fynn van Westen; [2022]
    Nyckelord :BERT; Language-Modelling; Cyber-Security; Intrusion-Detection; NLP; Anomaly-Detection; One-Class-Classification; BERT; språkmodellering; cybersäkerhet; intrångsdetektering; NLP; anomalidetektering; en-klass-klassificering;

    Sammanfattning : Intrusion detection is the most prominent topic of modern computer network security. The potential attack surface is growing exponentially every year. To cope with the amounts of data which accrue, automated methods for detecting undesired network activity are the only feasible solution. LÄS MER