Details

Oblikoskladenjsko označevanje slovenskega jezika z globokimi nevronskimi mrežami
ID Belej, Primož (Author), ID Robnik Šikonja, Marko (Mentor) More about this mentor... This link opens in a new window, ID Krek, Simon (Comentor)

.pdfPDF - Presentation file, Download (4,95 MB)
MD5: 93613CCF380E4F794BB8825859E333F3

Abstract
V magistrskem delu se ukvarjamo z oblikoskladenjskim označevanjem slovenskega jezika. Pri tej nalogi s področja obdelave naravnega jezika povedim priredimo ustrezno zaporedje oznak, ki opisujejo oblikoskladenjske lastnosti besed. Za razliko od tipičnih pristopov, ki vhodne povedi obravnavajo na nivoju besed, naša rešitev obravnava vhodne povedi kot zaporedja znakov. Nalogo označevanja rešujemo s kombinacijo konvolucijskih in rekurentnih nevronskih mrež. Posebnost našega pristopa je tudi v sami naravi označevanja, saj ga ne obravnavamo kot problem večrazredne klasifikacije, temveč kot večznačno klasifikacijo, kjer primerom dodeljujemo oznake. Z namenom izboljšave rezultatov našo rešitev združimo v ansambel treh označevalnikov, skupaj z dvema obstoječima označevalnikoma za slovenski jezik. Ob primerjavi naše rešitve z obstoječimi ugotovimo, da predlagana rešitev dosega najboljše rezultate pri reševanju zadanega problema.

Language:Slovenian
Keywords:strojno učenje, oblikoskladenjsko označevanje, globoko učenje, konvolucijske nevronske mreže, rekurentne nevronske mreže, ansambli klasifikatorjev
Work type:Master's thesis/paper
Organization:FRI - Faculty of Computer and Information Science
Year:2018
PID:20.500.12556/RUL-105266 This link opens in a new window
Publication date in RUL:16.11.2018
Views:3108
Downloads:398
Metadata:XML DC-XML DC-RDF
:
BELEJ, Primož, 2018, Oblikoskladenjsko označevanje slovenskega jezika z globokimi nevronskimi mrežami [online]. Master’s thesis. [Accessed 5 April 2025]. Retrieved from: https://repozitorij.uni-lj.si/IzpisGradiva.php?lang=eng&id=105266
Copy citation
Share:Bookmark and Share

Secondary language

Language:English
Title:Part of speech tagging of slovene language using deep neural networks
Abstract:
The thesis deals with part of speech tagging of Slovene language. Part of speech tagging is a process of matching sentences in natural language with a sequence of suitable tags, which contain information about parts of speech and morphological properties of words. Our solution uses character-level representation of words, which is different from typical solutions, which process input sentences as sequences of words. Our part of speech tagger is implemented using convolutional and recurrent neural networks. Unlike common approaches that address this problem as multi-class classification, our solution proposes a multi-label classification approach. In order to improve our results we implement an ensemble of three part of speech taggers. When comparing our solution with existing ones, we find that the proposed solution achieves the best results.

Keywords:machine learning, part-of-speech tagging, deep learning, convolutional neural networks, recurrent neural networks, ensemble classifiers

Similar documents

Similar works from RUL:
  1. Antimicrobial activity and biodegradation of natural cellulose fibre blends with embedded ZnO
  2. Antibacterial activity of didecydimethylammonium chloride
  3. Feline otitis externa caused by methicillin-resistant Staphylococcus aureus with mixed hemolytic phenotype and overview of possible genetic backgrounds
  4. Antimicrobial resistance and molecular characterization of methicillin-resistant Staphylococcus aureus from two pig farms
  5. Inhibition of MurA enzyme from Escherichia coli and Staphylococcus aureus by diterpenes from Lepechinia meyenii and their synthetic analogs
Similar works from other Slovenian collections:
  1. COMPARISON OF CLASSICAL INCUBATING METHODS ON SELECTIVE AGAR MEDIA AND MOLECULAR METHODS OF POLYMERASE CHAIN REACTION FOR ANALYSIS OF ARTIFICIALLY CONTAMINATED TEXTILES
  2. Structural basis of human clamp sliding on DNA
  3. Enterohemorrhagic Escherichia coli O157

Back