diplomsko delo

Abstract

V diplomski nalogi smo preizkusili metodo za izboljšavo klasifikacije globokih nevronskih mrež s predznanjem o negaciji. Najuspešnejši jezikovni modeli, kot na primer BERT ali ELMo, so uspešni pri klasifikaciji besedil, a odpovejo pri negaciji. Prednaučene jezikovne modele smo prilagodili, da tudi v slovenščini bolje delujejo z negacijo. To smo dosegli z spreminjanjem funkcije izgube nevronske mreže ter prilagajanjem obstoječih modelov. Metodo smo preizkusili na prilagojenem korpusu z dodanimi negacijami osnovnih stavkov. Metoda je uspešno zmanjšala delež napačnih napovedi v negiranih stavkih pri maskiranem jezikovnem modelu, točnost na nalogah iz slovenske zbirke SuperGLUE pa je ponekod izboljšala, drugje pa poslabšala.

Keywords

globoke nevronske mreže;klasifikacija;obravnava negacije;veliki vnaprej naučeni jezikovni modeli;univerzitetni študij;diplomske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.11 - Undergraduate Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [M. Kranjec]
UDC: 004.8:81'322.2(043.2)
COBISS: 121785859 Link will open in a new window
Views: 31
Downloads: 13
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Improving negation handling in large language models
Secondary abstract: In the thesis we have tested a method for improved classification of deep neural networks with prior knowledge of negation. State of the art language models, such as ELMo and BERT, are successful at text classification, but fail when there is negation involved. We adjusted pre-trained language models to work better with negation in Slovene. We modified the loss function of the neural networks and retrained the models. We have tested the method on a modified corpus with added negations of original sentences. The method successfully reduced the error in the negated sentences for masked language models, and it increased the accuracy for some tasks from the Slovene version of the SuperGLUE benchmark but decreased for others.
Secondary keywords: deep neural networks;classification;negation modeling;large pretrained language models;computer science;diploma;Nevronske mreže (računalništvo);Računalništvo;Univerzitetna in visokošolska dela;
Type (COBISS): Bachelor thesis/paper
Study programme: 1000468
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 27 str.
ID: 16382221