izpis_h1_title_alt

Postavljanje vejic v slovenščini s pomočjo strojnega učenja
Krajnc, Anja (Author), Robnik Šikonja, Marko (Mentor) More about this mentor... This link opens in a new window

.pdfPDF - Presentation file, Download (444,77 KB)
MD5: EAEA283DC9BB1537D6B529FA34EB294B

Abstract
Cilj diplomske naloge se je naučiti postavljanja vejic s strojnim učenjem. Naš pristop temelji na generiranju novih atributov na podlagi slovničnih pravil za slovenski jezik, ki z dodatno informacijo omogočijo boljše učenje, tj. višjo natančnost in priklic. Osredotočili smo se na postavljanje vseh vejic v besedilu. Izhajali smo iz že obstoječe raziskave za postavljanje vejic v slovenščini, ki smo jo dopolnili z drugačnimi metodami učenja, drugačnimi parametri, vzorčenjem neuravnoteženih množic ter z dodatnimi informativnimi atributi. Za analizo smo uporabili korpus Šolar in izboljšano verzijo tega korpusa. Za modeliranje smo uporabili sistem za strojno učenje WEKA. Najboljše rezultate smo dosegli z algoritmi naključna drevesa, alternirajoče odločitveno drevo ter odločitvena tabela.

Language:Slovenian
Keywords:procesiranje naravnega jezika, obdelava jezika, slovenski jezik, vejica, ločila, jezikovne tehnologije, naključni gozdovi, SVM, prečno preverjanje, podvzorčenje, strojno učenje.
Work type:Bachelor thesis/paper (mb11)
Organization:FRI - Faculty of computer and information science
Year:2015
Views:1712
Downloads:346
Metadata:XML RDF-CHPDL DC-XML DC-RDF
 
Average score:(0 votes)
Your score:Voting is allowed only to logged in users.
:
Share:AddThis
AddThis uses cookies that require your consent. Edit consent...

Secondary language

Language:English
Title:Using machine learning for placing comma in Slovene
Abstract:
We aim to learn comma placing using machine learning. Our approach is based on adding new attributes created from grammatical rules for the Slovenian language, which provides more information and thus enable better learning, i.e., higher precision and recall. We focus on placing all the commas in the text. We modify an existing research with additional learning methods, different parameters, undersampling and knowledge based attributes. We use corpus Šolar and improved corpus Šolar for testing and machine learning toolkit WEKA. Best results were achieved with random forests, alternating decision tree and decision table models.

Keywords:natural language processing, language manipulation, Slovenian language, comma, punctuation mark, language technologies, random forest, SVM, cross-validation, undersampling, machine learning.

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Comments

Leave comment

You have to log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back