Sökning: "Summarization"

Visar resultat 16 - 20 av 76 uppsatser innehållade ordet Summarization.

  1. 16. FINE-TUNE A LANGUAGE MODEL FOR TEXT SUMMARIZATION (BERTSUM) ON EDGAR-CORPUS

    Master-uppsats, Uppsala universitet/Statistiska institutionen

    Författare :Yijie Niu; [2022]
    Nyckelord :Machine Learning; Natural Language Processing; Text Summarization; Transformers; Neural Networks;

    Sammanfattning : Financial reports include a lot of useful information for investors, but extracting this information is time-consuming. We think text summarization is a feasible method. In this thesis, we implement BERTSUM, a state-of-the-art language model for text summarization, and evaluate the results by ROUGE metrics. LÄS MER

  3. 17. SARS-CoV-2 Lineage Clustering : Using Unsupervised Machine Learning

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

    Författare :Amanda Hedlund; Fonzie Forsman; [2022]
    Nyckelord :;

    Sammanfattning : The methods of sequencing genetic information and the access to this information has proved to be very useful in the research and understanding of viruses. It can for example be used to develop vaccines, manage pandemics, and attempt to map the virus’ spread and development. LÄS MER

  4. 18. Information Extraction and Design of An Assisted QA system in Motor Design

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

    Författare :Hongyi Luo; [2022]
    Nyckelord :Motor Design; PEGASUS; Question and Answer System; Text Summarization; Natural Language Processing; Deep Learning; Motorkonstruktion; PEGASUS; fråge- och svarssystem; sammanfattning av text; behandling av naturligt språk; djupinlärning;

    Sammanfattning : The Linz Center of Mechatronics’ SymSpace platform is designed to provide intelligent design and training for the traditional engineer training and industrial design approach in the field of motor design, which relies on the engineer’s own experience and manual work. This paper first analyzes and explores the usage patterns and possible improvement perspectives of motor design components using SymSpace user data. LÄS MER

  5. 19. Creating eye-catching headlines using BART

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

    Författare :Eva Despinoy; [2022]
    Nyckelord :Transformer; Natural Language Processing; Automatic Text Summarization; Headline Generation; BART;

    Sammanfattning : Social media is a significant factor in information distribution today, and this information landscape contains a lot of different posts that compete for the user’s attention. Different factors can help catch the interest of the user, and one of them is the headline of the message. LÄS MER

  7. 20. Automatic Podcast Chapter Segmentation : A Framework for Implementing and Evaluating Chapter Boundary Models for Transcribed Audio Documents

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

    Författare :Adam Feldstein Jacobs; [2022]
    Nyckelord :Machine Learning; Natural Language Processing; Speech Technology; Deep Learning; Podcast Segmentation; Maskininlärning; Språkteknologi; Djupinlärning; Podcast Segmentation;

    Sammanfattning : Podcasts are an exponentially growing audio medium where useful and relevant content should be served, which requires new methods of information sorting. This thesis is the first to look into the state-of-art problem of segmenting podcasts into chapters (structurally and topically coherent sections). LÄS MER