Zpět na vyhledávání

Bc. Veronika Mitická

Bachelor's thesis

Automatic part-of-speech prediction based on prior annotation.

Automatic part-of-speech prediction based on prior annotation.
Abstract:
Cieľom tejto bakalárskej práce je zjednodušiť proces manuálnej anotácie dát pre jazyky s malým množstvom anotovaných dát. Práca integruje automatický proces do existujúceho nástroja na anotáciu korpusov s názvom CORAT. Vylepšenie sa zameriava na predvypĺňanie slovných druhov a základných tvarov slov, čo zefektívňuje prácu anotátorov. Prvým implementovaným prístupom je odhadovanie značiek a základných …more
Abstract:
This bachelor thesis aims to simplify the manual annotation process of low-resource languages by integrating automatic processing into the existing Corpus Annotation tool (CORAT). The enhancement focuses on pre-filling POS tags and lemmas to streamline the annotators' work. The first method implemented relies on guessing words based solely on their frequency in a database. Additionally, the thesis …more
 

Keywords

manual annotation RFTagger CSTlemma low-resource languages corpus annotation tool CORAT POS tagging lemmatization machine learning
 
Language used: English
Date on which the thesis was submitted / produced: 23. 5. 2024
Identifier: https://is.muni.cz/th/nau1q/

Thesis defence

  • Date of defence: 25. 6. 2024
  • Supervisor: RNDr. Marek Medveď, Ph.D.
  • Reader: RNDr. Vojtěch Kovář, Ph.D.

Citation record

Cite this text

Full text of thesis

Contents of on-line thesis archive
Published in Theses:
  • světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: Masarykova univerzita, Fakulta informatiky
Složka Reference to the local database directory of the institution

Masaryk University

Faculty of Informatics

Bachelor programme / field:
Programming and development / Programming and development

Theses on a related topic

List of theses with an identical keyword.
  • No theses on a related topic available.