Sökning: "language normalisation"

Visar resultat 1 - 5 av 11 avhandlingar innehållade orden language normalisation.

  1. 1. Natural Language Processing for Low-resourced Code-switched Colloquial Languages – The Case of Algerian Language

    Författare :Wafia Adouane; Göteborgs universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Natural language processing; Deep neural networks; Low-resourced language; Colloquial language; Code-switch; Dialectal Arabic; User-generated data; Non-standardised orthography; Algerian language;

    Sammanfattning : In this thesis we explore to what extent deep neural networks (DNNs), trained end-to-end, can be used to perform natural language processing tasks for code-switched colloquial languages lacking both large automated data and processing tools, for instance tokenisers, morpho-syntactic and semantic parsers, etc. We opt for an end-to-end learning approach because this kind of data is hard to control due to its high orthographic and linguistic variability. LÄS MER

  3. 2. Normaliserade föräldrar : en undersökning av Försäkringskassans broschyrer 1974–2007

    Författare :Lena Lind Palicki; Håkan Åbrink; Gunilla Byrman; Örebro universitet; []
    Nyckelord :HUMANIORA; HUMANITIES; Försäkringskassan; Swedish Social Insurance Agency; parental leave; intersectionality; discourse analysis; normalisation; brochures; deixis; address; governmentality; Swedish; authority language; feminist discourse analysis; categorisation; Försäkringskassan; föräldraledighet; intersektionalitet; diskursanalys; normalisering; broschyrer; deixis; tilltal; governmentalitet; svenska; myndighetsspråk; språk och kön; feministisk diskursanalys; kategorisering; Swedish language; Svenska språket; Svenska språket; Swedish Language;

    Sammanfattning : The main purpose of this dissertation is to analyse and identify problems arising from the Swedish Social Insurance Agency’s (SSIA) perceptions of parents, as they appear in the brochures targeted at expectant or new parents between 1974 and 2007. The aim is to distinguish who are being pointed out, constructed, and normalised as parents; and to analyse the functions of the recipients and the senders respectively. LÄS MER

  4. 3. Språk och rasism : Privilegiering och diskriminering i offentlig, medierad interaktion

    Författare :Karin Hagren Idevall; Anna-Malin Karlsson; Lena Lind Palicki; Lann Hornscheidt; Uppsala universitet; []
    Nyckelord :HUMANIORA; HUMANITIES; actor-network theory; banal nationalism; comments sections; discourse analysis; discrimination; internet; language and racism; political discourse; privileging; public debate; whiteness; Nordiska språk; Scandinavian Languages;

    Sammanfattning : This PhD thesis concerns language and racism. The aim is to explore how racism is reproduced in interaction in public debates on immigration, integration and refugee policy. LÄS MER

  5. 4. Implicit and explicit norm in contemporary Russian verbal stress

    Författare :Elisabeth Marklund Sharapova; Sven Gustavsson; Ludmila Ferm; Lars Steensland; Uppsala universitet; []
    Nyckelord :HUMANIORA; HUMANITIES; Slavic and Baltic languages - general; language norm; implicit norm; explicit norm; language normativisation; language normalisation; codification; Russian; stress; verbal stress; accentology; orthoepy; Slaviska och baltiska språk - allmänt; Slavic languages; Slaviska språk; Slaviska språk; Slavic Languages;

    Sammanfattning : The purpose of this thesis is to investigate norm in contemporary Russian verbal stress. In a first step the concept of norm is explored. It is shown that the criteria generally used in Russian for defining norm (correspondence to the language system, usage and authority/tradition/necessity) are not applied strictly. LÄS MER

  7. 5. Spelling Normalisation and Linguistic Analysis of Historical Text for Information Extraction

    Författare :Eva Pettersson; Joakim Nivre; Beáta Megyesi; Michael Piotrowski; Uppsala universitet; []
    Nyckelord :NLP for historical text; spelling normalisation; digital humanities; information extraction; character-based statistical machine translation; SMT; Levenshtein edit distance; language technology; computational linguistics; Computational Linguistics; Datorlingvistik;

    Sammanfattning : Historical text constitutes a rich source of information for historians and other researchers in humanities. Many texts are however not available in an electronic format, and even if they are, there is a lack of NLP tools designed to handle historical text. LÄS MER