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

Using deep convolutional neural networks on natural language problems

Žiga Pušnik (2015) Using deep convolutional neural networks on natural language problems. EngD thesis.

Download (970Kb)


    The thesis examines the learning of language problems with convolutional neural networks. Convolutional neural networks were developed for machine vision. We used them to classify short abstracts and to learn a comma placement in Slovenian language. We programmed our convolutional neural network in programming language python with Theano library. Our work is based on existing research. We describe adaptation of datasets to our model. Several experiments were conducted and we compared lemmatization versus stemming and vector representation of text versus byte array representation. The best results were obtained with text quantized with 1 to m encoding. Comma placing results are comparable with other machine learning approaches.

    Item Type: Thesis (EngD thesis)
    Keywords: machine learning, natural language processing, neural network, neuron, convolution, convolutional neural netvork, clasification, clasification model, clasificator, clasification accuracy, language, text, comma, lemma, stemm, momentum, gradient descent, backpropagation, text corpus , attribute
    Number of Pages: 47
    Language of Content: Slovenian
    Mentor / Comentors:
    Name and SurnameIDFunction
    izr. prof. dr. Marko Robnik Šikonja276Mentor
    Link to COBISS: http://www.cobiss.si/scripts/cobiss?command=search&base=51012&select=(ID=1536476611)
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Item ID: 3052
    Date Deposited: 08 Sep 2015 13:21
    Last Modified: 17 Sep 2015 12:06
    URI: http://eprints.fri.uni-lj.si/id/eprint/3052

    Actions (login required)

    View Item