Semantic vector spaces : a Finnish perspective
Abstract
Tässä tutkielmassa käsitellään semanttisia vektoriavaruuksia, sekä laskennallista kielitiedettä suomen kielen näkökulmasta. Tutkielmassa esitellään
kielitieteellinen viitekehys, jonka puitteissa matemaattinen kielenmallinus tapahtuu. Vektoriavaruuksien ominaisuuksia tarkastellaan kolmen mallin puitteissa. Mallien perustella
osoitetaan, että semanttiset vektoriavaruusmallit kykenevät mallintamaan semanttisia merkityksiä lähdetekstin mukaisesti.
In this thesis we explore semantic vector spaces and computational linguistics from the perspective of the Finnish language. We present the linguistic landscape surrounding mathematical language modeling. The properties of semantic vector spaces are studied using three models. The models indicate that semantic vector space models are capable of representing semantic meanings according as it occurred in the source data.
In this thesis we explore semantic vector spaces and computational linguistics from the perspective of the Finnish language. We present the linguistic landscape surrounding mathematical language modeling. The properties of semantic vector spaces are studied using three models. The models indicate that semantic vector space models are capable of representing semantic meanings according as it occurred in the source data.
Main Author
Format
Theses
Master thesis
Published
2019
Subjects
The permanent address of the publication
https://urn.fi/URN:NBN:fi:jyu-201909034010Use this for linking
Language
English
License
The record contains restricted files. You can request a copy of this thesis here.
The material is available for reading at the archive workstation of the University of Jyväskylä Library.
The material is available for reading at the archive workstation of the University of Jyväskylä Library.
Tekijä ei ole antanut lupaa avoimeen julkaisuun, joten aineisto on luettavissa vain Jyväskylän yliopiston kirjaston arkistotyösemalta. Ks. https://kirjasto.jyu.fi/fi/tyoskentelytilat/laitteet-ja-tilat..