University of Jyväskylä | JYX Digital Repository

  • English  | Give feedback |
    • suomi
    • English
 
  • Login
JavaScript is disabled for your browser. Some features of this site may not work without it.
View Item 
  • JYX
  • Opinnäytteet
  • Pro gradu -tutkielmat
  • View Item
JYX > Opinnäytteet > Pro gradu -tutkielmat > View Item

Word sense disambiguation for Finnish with an application to language learning

Thumbnail
View/Open
1.1Mb

Downloads:  
Show download detailsHide download details  
Authors
Robertson, Frankie
Date
2020
Discipline
TietotekniikkaMathematical Information Technology
Copyright
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.

 
Tehtävää sanan oikean merkityksen määritämiseksi automattisesti jossakin luonnollisen kielen ilmaisussa kutsutaan saneiden alamerkitysten yksiselitteistämiseksi. Tämä pro gradu -tutkielma kuvaa saneiden alamerkitysten yksiselitteistämisen itoimeenpanoa ja arviointia suomen kielelle, ja sitä motivoi tämän tehtävän uudenlainen soveltaminen tietokoneavusteiseen kielen oppimiseen. Tutkielmassa kaksikieliseen tekstitysaineistoon pohjaava sanojen alamerkitysten mukaan annotoitu korpus on luotu automattisesti palvelemaan opetusaineistona koneoppimiseen pohjautuville saneiden alamerkitysten yksiselitteistämisen tekniikoille. Seuravaksi saneiden alamerkitysten yksiselitteistämisen algoritmeja on muokattu suomen kielelle ja arvioitu niiden F1-mitan mukaan. Sen jälkeen on rakennettu sekä leksikaalinen tietämyskanta klusteroimalla ja tunnistamalla vastaavuuksia että välineet kompleksisten lekseemien poimimiseen ja analysointiin. Lopuksi on esitelty NiinMikäOli?!, tietokoneavusteinen kielen oppimisen väline, joka käyttää saneiden alamerkitysten yksiselitteistämistä uudella leksikaalisella resurssilla tarjotakseen sanojen rakenteeseen ja merkitykseen liittyvää kontekstisidonaista apua kielenoppijoille. Lisäksi on selitetty NiinMikäOli?!:n rakentamista ja käyttöliittymää ohjaavat suunnittelun periaatteet. ...
 
The task of automatically determining the correct meaning of a word within some natural language utterance is referred to as Word Sense Disambiguation (WSD). This thesis describes the implementation and evaluation of WSD for the Finnish language, motivated by its novel application to Computer Aided Language Learning (CALL). To serve as training data for Machine Learning (ML) based WSD techniques, a sense-annotated corpus is automatically created based on a collection of bilingual subtitles. Next, several WSD algorithms are adapted to Finnish and evaluated according to their F1-measure. Then, a Lexical Knowledge Base (LKB) is constructed by clustering and aligning existing resources, and tools to extract and analyse complex lexical units are created. Finally, TheWhatNow?!, a CALL tool which uses WSD on this new lexical resource to offer in context help related to word structure and meaning to language learners is introduced and the design principles guiding its construction and user interface are expounded. ...
 
Keywords
word sense disambiguation computer aided language learning saneiden alamerkitysten yksiselitteistäminen tietokoneavusteinen kielen oppiminen muoto-oppi (kielitiede) tietokoneavusteinen oppiminen sanasemantiikka kieli ja kielet kieliteknologia tietokonelingvistiikka suomen kieli kielen oppiminen arviointi toinen kieli morphology (grammar) computer-assisted learning lexical semantics languages language technology computer linguistics Finnish language language learning evaluation second language
URI

http://urn.fi/URN:NBN:fi:jyu-202004072692

Metadata
Show full item record
Collections
  • Pro gradu -tutkielmat [23369]

Related items

Showing items with similar title or keywords.

  • The dynamics of foreign versus second language development in Finnish writing 

    Tilma, Corinne (University of Jyväskylä, 2014)
  • Show, Don't Tell : Visualising Finnish Word Formation in a Browser-Based Reading Assistant 

    Robertson, Frankie (LiU Electronic Press, 2020)
    This paper presents the NiinMikaOli?! reading assistant for Finnish. The focus is upon the simplified presentation and visualisation of a wide range of word-level linguistic phenomena of the Finnish language in a unified ...
  • Learning to read for the first time as adult immigrants in Finland : Reviewing pertinent research of low-literate or non-literate learners’ literacy acquisition and computer-assisted literacy training 

    Malessa, Eva (Centre for Applied Language Studies, University of Jyväskylä, 2018)
    Against the backdrop of increasing global humanitarian migration to highly literate countries and the resulting necessity and challenge to provide language and literacy education to non-literate or low-literate adult second ...
  • GraphoLearn India : The Effectiveness of a Computer-Assisted Reading Intervention in Supporting Struggling Readers of English 

    Patel, Priyanka; Torppa, Minna; Aro, Mikko; Richardson, Ulla; Lyytinen, Heikki (Frontiers Research Foundation, 2018)
    India, a country with a population of more than 1.3 billion individuals, houses the world’s second largest educational system. Despite this, 100 of millions of individuals in India are still illiterate. As English medium ...
  • Learning Grammar for Social Action : Implications for Research and Language Teaching 

    Piirainen-Marsh, Arja; Lilja, Niina (Wiley, 2022)
  • Browse materials
  • Browse materials
  • Articles
  • Conferences and seminars
  • Electronic books
  • Historical maps
  • Journals
  • Tunes and musical notes
  • Photographs
  • Presentations and posters
  • Publication series
  • Research reports
  • Research data
  • Study materials
  • Theses

Browse

All of JYXCollection listBy Issue DateAuthorsSubjectsPublished inDepartmentDiscipline

My Account

Login

Statistics

View Usage Statistics
  • How to publish in JYX?
  • Self-archiving
  • Publish Your Thesis Online
  • Publishing Your Dissertation
  • Publication services

Open Science at the JYU
 
Data Protection Description

Accessibility Statement

Unless otherwise specified, publicly available JYX metadata (excluding abstracts) may be freely reused under the CC0 waiver.
Open Science Centre