Sökning: "Frågegenerering"

Visar resultat 1 - 5 av 6 uppsatser innehållade ordet Frågegenerering.

  1. 1. Extracting relevant answer phrases from text : For usage in reading comprehension question generation

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

    Författare :Filippa Kärrfelt; [2022]
    Nyckelord :Answer phrase extraction; Question generation; BERT; Reading comprehension; Neural networks; Extrahering av svarsfraser; Frågegenerering; BERT; Läsförståelse; Neurala nätverk;

    Sammanfattning : This report presents a method for extracting answer phrases, suitable as answers to reading comprehension questions, from Swedish text. All code used to produce the results is available on github*. The method is developed using a Swedish BERT, a pre-trained language model based on neural networks. LÄS MER

  3. 2. The UX of AI-Augmented Question Generation

    Master-uppsats, Lunds universitet/Ergonomi och aerosolteknologi

    Författare :Hanna Tydén; Inger Gundersen; [2021]
    Nyckelord :Interaction Design; User Experience; Question Generation; Usability Testing; E-learning; Technology and Engineering;

    Sammanfattning : The demand for improved digital learning tools has increased over the recent years, and got an additional boost from the Covid-19-pandemic. Many companies use artificial intelligence to improve their systems, one use case being question generation. LÄS MER

  4. 3. Automatic Question Generation with Pre-trained Masked Language Models

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

    Författare :Chun Hung Lin; [2020]
    Nyckelord :;

    Sammanfattning : In this project, we study the task of generating a question from a given passage-answer pair using pre-trained masked language models. Asking questions is of importance in artificial intelligence development because it makes a machine look intelligent when it raises a reasonable and well-constructed question. LÄS MER

  5. 4. Automating Question Generation Given the Correct Answer

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

    Författare :Haoliang Cao; [2020]
    Nyckelord :Natural Language Processing; NLP; Natural Language Generation; NLG; Question Generation; Naturligtspråkbehandling; Naturligtspråkgenerering; Frågegenerering;

    Sammanfattning : In this thesis, we propose an end-to-end deep learning model for a question generation task. Given a Wikipedia article written in English and a segment of text appearing in the article, the model can generate a simple question whose answer is the given text segment. The model is based on an encoder-decoder architecture. LÄS MER

  7. 5. Using Word Embedding to Generate Cloze Sentences

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

    Författare :Alex Diaz; Daniel Peng; [2020]
    Nyckelord :;

    Sammanfattning : Creating cloze sentences—contextual fill-in-the-blanks questions—can be time consuming and challenging. While research has been done on automatic question generation, a problem within this area is the high complexity of processing text and constructing relevant questions. LÄS MER