Sökning: "Automatic Text Simplification"

Visar resultat 1 - 5 av 13 uppsatser innehållade orden Automatic Text Simplification.

  1. 1. 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

  3. 2. Text simplification in Swedish using transformer-based neural networks

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

    Författare :Samuel Söderberg; [2023]
    Nyckelord :Machine learning; Natural language processing; Text simplification; Datasets; Maskininlärning; Neurolingvistisk programmering; Textförenkling; Dataset;

    Sammanfattning : Textförenkling innebär modifiering av text så att den blir lättare att läsa genom ersättning av komplexa ord, ändringar av satsstruktur och/eller borttagning av onödig information. Forskning existerar kring textförenkling på svenska, men användandet av neurala nätverk inom området är begränsat. LÄS MER

  4. 3. Controllable sentence simplification in Swedish : Automatic simplification of sentences using control prefixes and mined Swedish paraphrases

    Master-uppsats, Linköpings universitet/Institutionen för datavetenskap

    Författare :Julius Monsen; [2023]
    Nyckelord :NLP; automatic text simplification; paraphrase mining; prefix-tuning; control prefixes; BART;

    Sammanfattning : The ability to read and comprehend text is essential in everyday life. Some people, including individuals with dyslexia and cognitive disabilities, may experience difficulties with this. Thus, it is important to make textual information accessible to diverse target audiences. LÄS MER

  5. 4. Exploring Automatic Synonym Generation for Lexical Simplification of Swedish Electronic Health Records

    Master-uppsats, Linköpings universitet/Institutionen för hälsa, medicin och vård

    Författare :Anna Jänich; [2023]
    Nyckelord :Lexical Simplification; EHR; Electronic Health Records; Swedish EHRs; patient records; complex medical terminology; synonym generation; synonym replacement; Word2Vec; BERT; NLP; ML;

    Sammanfattning : Electronic health records (EHRs) are used in Sweden's healthcare systems to store patients' medical information. Patients in Sweden have the right to access and read their health records. Unfortunately, the language used in EHRs is very complex and presents a challenge for readers who lack medical knowledge. LÄS MER

  7. 5. Readability Assessment with Pre-Trained Transformer Models : An Investigation with Neural Linguistic Features

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

    Författare :Chuchu Ma; [2022]
    Nyckelord :Readability Assessment; Pre-trained Transformer Models; Neural Linguistic Features;

    Sammanfattning : Readability assessment (RA) is to assign a score or a grade to a given document, which measures the degree of difficulty to read the document. RA originated in language education studies and was used to classify reading materials for language learners. Later, RA was applied to many other applications, such as aiding automatic text simplification. LÄS MER