Statistični generator besedil v slovenskem jeziku

diplomsko delo univerzitetnega študijskega programa

Goran Petrović (Author), Mirjam Sepesy Maučec (Mentor), Andrej Žgank (Co-mentor)

Abstract

V diplomskem delu smo se posvetili generatorjem besedil. Opravili smo analizo obstoječih generatorjev in izdelali preprost eksperimentalni generator besedil, ki tvori besedila v slovenskem jeziku. Temelji na statistiki n-gramov. Za izdelavo programa smo uporabili okolje Code::Blocks, na voljo smo imeli sezname frekvenc besednih unigramov, bigramov in trigramov ter n-gramov z MSD-oznakami. Analizirali smo tvorjena besedila iz dveh scenarijev in podali rezultate ter končni sklep uporabe n-gramov z MSD-oznakami in brez njih.

Keywords

generator besedil v naravnem jeziku;Markove verige;n-gramski modeli;

Data

Language:	Slovenian
Year of publishing:	2012
Source:	Maribor
Typology:	2.11 - Undergraduate Thesis
Organization:	UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher:	[G. Petrović]
UDC:	004.93:621.39(043.2)
COBISS:	16424726
Views:	1375
Downloads:	98
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Statistical generator of text in Slovenian language
Secondary abstract:	The diploma work analyse text generators. We developed a simple experimental text generator, that generates text in Slovenian language based on n-gram statistics. During the process of development we used Code::Blocks environment and lists of unigrams, bigrams and trigrams of words and n-grams with MSD tags attached. Generated sentences in both scenarios were analyzed and results were presented. We also made a conclusion about using word n-grams and n-grams with MSD tags.
Secondary keywords:	natural language;Markov chain;n-gram models;
URN:	URN:SI:UM:
Type (COBISS):	Bachelor thesis/paper
Thesis comment:	Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Telekomunikacije
Pages:	IX, 38 f.
Keywords (UDC):	science and knowledge;organization;computer science;information;documentation;librarianship;institutions;publications;znanost in znanje;organizacije;informacije;dokumentacija;bibliotekarstvo;institucije;publikacije;prolegomena;fundamentals of knowledge and culture;propaedeutics;prolegomena;splošne osnove znanosti in kulture;computer science and technology;computing;data processing;računalniška znanost in tehnologija;računalništvo;obdelava podatkov;application-oriented computer-based techniques;računalniške tehnike za namensko rabo;aplikativno usmerjene računalniško podprte tehnike;pattern information processing;obdelava informacij v vzorcih;applied sciences;medicine;technology;uporabne znanosti;medicina;tehnika;engineering;technology in general;inženirstvo;tehnologija na splošno;mechanical engineering in general;nuclear technology;electrical engineering;machinery;strojništvo;electrical engineering;elektrotehnika;
ID:	999366