Sökning: "get corpus"

Visar resultat 1 - 5 av 32 uppsatser innehållade orden get corpus.

  1. 1. REDUPLICATED FORM OF ADJECTIVES IN SOMALI: A plural form or something else?

    Master-uppsats, Göteborgs universitet/Institutionen för språk och litteraturer

    Författare :Ahmed Abdulqaadir Sheikh; [2023-06-21]
    Nyckelord :Somali; adjective; reduplication; agreement; distributivity;

    Sammanfattning : Abstract The Somali adjectives gets reduplicated. This form of the adjective usually follows the nouns in the plural and the base form follows the nouns in the singular. The thesis aims to study the form and function of the reduplication of the adjectives (in contrast with the base form). LÄS MER

  3. 2. Analysing CSR reporting over the years, company size, region, and sector through dictionary-based text mining

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

    Författare :Anuj Singhvi; Dorna Jahangoshay Sarijlou; [2023]
    Nyckelord :Corporate Social Responsibility; Sustainability Reporting; Natural Language Processing; Text Mining; CSR Dictionaries;

    Sammanfattning : As Corporate Social Responsibility (CSR) reports become more prevalent and systematised, there is a strong need to develop approaches that seek to analyse the contents of these reports. In this thesis, we present two valuable contributions. LÄS MER

  4. 3. Synthetic data generation for domain adaptation of a retriever-reader Question Answering system for the Telecom domain : Comparing dense embeddings with BM25 for Open Domain Question Answering

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

    Författare :Filip Döringer Kana; [2023]
    Nyckelord :Natural Language Processing; Transformers; Deep Learning; Question Answering; Data Generation; Språkteknologi; Transformers; Djupinlärning; Frågebesvaring; Datagenerering;

    Sammanfattning : Having computer systems capable of answering questions has been a goal within Natural Language Processing research for many years. Machine Learning systems have recently become increasingly proficient at this task with large language models obtaining state-of-the-art performance. LÄS MER

  5. 4. Semantic Topic Modeling and Trend Analysis

    Master-uppsats, Linköpings universitet/Statistik och maskininlärning

    Författare :Jasleen Kaur Mann; [2021]
    Nyckelord :NLP; unsupervised topic modelling; trend analysis; LDA; BERT; Sentence-BERT; TF-IDF; transformer based language models; document clustering;

    Sammanfattning : This thesis focuses on finding an end-to-end unsupervised solution to solve a two-step problem of extracting semantically meaningful topics and trend analysis of these topics from a large temporal text corpus. To achieve this, the focus is on using the latest develop- ments in Natural Language Processing (NLP) related to pre-trained language models like Google’s Bidirectional Encoder Representations for Transformers (BERT) and other BERT based models. LÄS MER

  7. 5. Análisis de errores gramaticales en el aula de ELE : Un estudio de la producción escrita y la producción oral en la escuela sueca

    Kandidat-uppsats, Högskolan Dalarna/Institutionen för språk, litteratur och lärande

    Författare :Laura Calvo Fernández; [2021]
    Nyckelord :Error analysis; grammatical category; written production; oral production; Spanish as a foreign language;

    Sammanfattning : The present study aimed to investigate and analyze the most frequent grammatical errors in both oral and written production, what causes the errors as well as the possible correlation that may exist between them by means of a quantitative and qualitative method.The sample selected to perform the investigation is composed of 23 students who study the eighth course in the primary Swedish school. LÄS MER