ePrints.FRI - University of Ljubljana, Faculty of Computer and Information Science

Prediction of stress of Slovenian words with machine learning methods

Luka Krsnik (2017) Prediction of stress of Slovenian words with machine learning methods. MSc thesis.

Download (594Kb)


    There is no simple algorithm for stress assignment of Slovene words. Speakers of Slovene are usually taught accents together with words. Machine learning algorithms give positive results on this problem, therefore we tried deep neural networks. We tested different architectures, data presentations and an ensemble of networks. We achieved the best results using the ensemble method, which correctly predicted 87,62 % of tested words. Our neural network approach improved results of other machine learning methods and proved to be successful in stress assignment.

    Item Type: Thesis (MSc thesis)
    Keywords: artificial inteligence, data mining, machine learning, deep neural networks, natural language processing, accentuation
    Number of Pages: 56
    Language of Content: Slovenian
    Mentor / Comentors:
    Name and SurnameIDFunction
    izr. prof. dr. Marko Robnik Šikonja276Mentor
    doc. dr. Tomaž ŠefComentor
    Link to COBISS: http://www.cobiss.si/scripts/cobiss?command=search&base=51012&select=(ID=1537581251)
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Item ID: 3978
    Date Deposited: 26 Sep 2017 14:39
    Last Modified: 10 Oct 2017 10:50
    URI: http://eprints.fri.uni-lj.si/id/eprint/3978

    Actions (login required)

    View Item