[feed] pefprints@pef.uni-lj.si | [feed] Atom [feed] RSS 1.0 [feed] RSS 2.0 |
  Logo Login | Create Account

Cross-lingual approach to abstractive summarization

Aleš Žagar (2020) Cross-lingual approach to abstractive summarization. MSc thesis.

Download (762Kb)


    Automatic text summarization is a process of extracting important information from texts and presenting that information in the form of a summary. Abstractive summarization approaches progressed using deep neural networks, but results are not yet satisfactory, especially for languages where large training sets do not exist. In several natural language processing tasks, cross-lingual model transfers are succesfully applied for low-resource languages where large enough datasets are not available. For summarization such cross-lingual transfer was so far not attempted due to non-reusable decoder side of neural models. In our work, we used a pretrained English summarization model based on deep neural networks and sequence-to-sequece architecture to summarize Slovene news articles. We solved the problem with inadequate decoder by using an additional language model for target language text generation. We developed five models with different training sample sizes. The results were assessed by automatic and human evaluation. Our cross-lingual model performance is similar to the existing Slovene abstractive summarizer. We also discuss some interdisciplinary aspects, raised by our work.

    Item Type: Thesis (MSc thesis)
    Keywords: automatic summarization, text generation, deep neural networks, language models, cross-lingual embeddings, abstractive summarization
    Number of Pages: 82
    Language of Content: Slovenian and English
    Mentor / Comentors:
    Mentor / ComentorsIDFunction
    prof. dr. Marko Robnik ŠikonjaMentor
    prof. dr. Igor FarkašComentor
    Link to COBISS: https://plus.si.cobiss.net/opac7/bib/peflj/20240131
    Institution: University of Ljubljana
    Department: Faculty of Education
    Item ID: 6262
    Date Deposited: 19 Jun 2020 12:33
    Last Modified: 19 Jun 2020 12:33
    URI: http://pefprints.pef.uni-lj.si/id/eprint/6262

    Actions (login required)

    View Item