prikaz prve stranice dokumenta Extending the recurrent neural network model for improved compositional modelling of text sequences
  Download
PDF 3.54 MB
doctoral thesis
Extending the recurrent neural network model for improved compositional modelling of text sequences
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. urn:nbn:hr:168:818357
Tutek, Martin
University of Zagreb
Faculty of Electrical Engineering and Computing
Department of Electronics, Microelectronics, Computer and Intelligent Systems

Institutional repository: FER Repository

Cite this document

Tutek, M. (2022). Extending the recurrent neural network model for improved compositional modelling of text sequences (Doctoral thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:818357

Tutek, Martin. "Extending the recurrent neural network model for improved compositional modelling of text sequences." Doctoral thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:818357

Tutek, Martin. "Extending the recurrent neural network model for improved compositional modelling of text sequences." Doctoral thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:818357

Tutek, M. (2022). 'Extending the recurrent neural network model for improved compositional modelling of text sequences', Doctoral thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 13 January 2025, https://urn.nsk.hr/urn:nbn:hr:168:818357

Tutek M. Extending the recurrent neural network model for improved compositional modelling of text sequences [Doctoral thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2022 [cited 2025 January 13] Available at: https://urn.nsk.hr/urn:nbn:hr:168:818357

M. Tutek, "Extending the recurrent neural network model for improved compositional modelling of text sequences", Doctoral thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:168:818357

Metadata
TitleExtending the recurrent neural network model for improved compositional modelling of text sequences
Title (croatian)Proširenje modela povratnih neuronskih mreža za poboljšano kompozicijsko modeliranje tekstnih sljedova
AuthorMartin Tutek
MentorJan Šnajder (mentor)
Committee memberSiniša Šegvić (predsjednik povjerenstva)
Committee memberMarko Čupić (član povjerenstva)
Committee memberGoran Glavaš (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
(Department of Electronics, Microelectronics, Computer and Intelligent Systems)
Zagreb
Defense date and country2022-07-22, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Universal decimal classification
(UDC)		004 - Computer science and technology. Computing. Data processing
Abstract
The thesis focuses on exploring extensions to the recurrent neural network (RNN) algorithm for natural language processing (NLP) in terms of improving its capabilities of semantic composition, investigating the possible benefits of leveraging multi-prototype word representations and improving its overall interpretability. While RNNs have received a strong competitor in form of the Transformer model, both approaches to processing natural language sequences possess their own set of issues. This thesis investigates methods of inducing sparsity in neural networks in order to learn shared sense representations and also tackles the problem of semantic composition in recurrent networks. The thesis introduces a novel approach for building recursive representations of language which is better suited to the hierarchical phrasal structure of language. The original scientific contributions of the thesis are: 1. Empirical analysis of the convergence of recurrent neural network algorithms on text sequence modeling tasks with respect to different input word representations; 2. An algorithm for learning word representations serving as input to text processing models based on contextualized word representations; 3. An extension of the recurrent neural network model for processing text sequences with mechanisms for processing linguistic phenomena such as polysemy, semantic composition, and coreference.
Abstract (croatian)
Središnje pitanje ovog doktorskog rada su proširenja algoritma povratnih neuronskih mreža (RNN) za obradu prirodnog jezika (NLP) u vidu poboljšanja semantičke kompozicije, nadogradnje kroz korištenje višeprototipnih reprezentacija riječi i sveukupno poboljšanje interpretabilnosti algoritma. Usprkos modelu Transformer koji predstavlja snažnu konkurenciju povratnim neuronskim mrežama, oba pristupa analizi teksta posjeduju svoje nedostatke. U okviru doktorskog rada istraženi su pristupi ugrađivanja rijetkosti u neuronske mreže s ciljem učenja dijeljenih reprezentacija značenja te problem semantičke kompozicije u povratnim mrežama. Doktorski rad uvodi novi, rekurzivni pristup građenju reprezentacija teksta prikladniji za specifičnosti jezika. Znanstveni doprinosi ovog doktorskog rada su: 1. Empirijska analiza konvergencije povratnih neuronskih mreža na zadacima analize teksta u ovisnosti o različitim ulaznim reprezentacijama riječi; 2. Algoritam učenja reprezentacija riječi baziran na kontekstualiziranim reprezentacijama riječi, s ciljem njihovog korištenja kao ulaza modelima obrade teksta; 3. Proširenje algoritma povratnih neuronskih mreža za obradu prirodnog jezika s naglaskom na obradu jezičnih fenomena poput polisemije, semantičke kompozicije i koreferenciranja.
Keywords
Keywords (croatian)
Languageenglish
URN:NBNurn:nbn:hr:168:818357
Promotion2022
Study programmeTitle: Computer Science
Study programme type: university
Study level: postgraduate
Academic / professional title: Doktor znanosti (Doktor znanosti)
Type of resourceText
Extentix, 93 str. : graf. prikazi ; 30 cm. + CD-ROM.
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2022-11-24 09:36:13