Linguistically-motivated automatic classification of Lithuanian texts for didactic purposes

Grigonytė, Gintarė; Kovalevskaitė, Jolanta; Rimkutė, Erika

doi:10.3233/978-1-61499-912-6-38

Use this url to cite publication: https://hdl.handle.net/20.500.12259/59511

Linguistically-motivated automatic classification of Lithuanian texts for didactic purposes

Type of publication

Straipsnis konferencijos medžiagoje Web of Science ir Scopus duomenų bazėje / Article in conference proceedings in Web of Science and Scopus database (P1a)

Author(s)

Author	Affiliation
Grigonytė, Gintarė	Stockholm University, Sweden	SE
Kovalevskaitė, Jolanta	Užsienio kalbų, lit. ir vert. s. katedra / Department of Foreign Language, Literary and Translation Studies	LT
Rimkutė, Erika	Lituanistikos katedra / Department of Lithuanian Studies	LT

Title

Linguistically-motivated automatic classification of Lithuanian texts for didactic purposes

[en]

Is part of

Human language technologies - the Baltic perspective: proceedings of the 8th international conference Baltic HLT, Tartu, Estonia, 27-29 September 2018 / editors K. Muischnek and K. Müürisep. Amsterdam : IOS Press, 2018

Date Issued

Date
2018

Publisher

Amsterdam : IOS Press, 2018

Publisher (trusted)

IOS Press

Is Referenced by

Scopus

Conference Proceedings Citation Index - Science (Web of Science)

Extent

p. 38-46

URI

URI
https://www.vdu.lt/cris/bitstream/20.500.12259/59511/2/ISBN9781614999119.PG_38-46.pdf
https://hdl.handle.net/20.500.12259/59511

DOI

10.3233/978-1-61499-912-6-38

Field of Science

Keywords (en)

Abstract (en)

This paper presents an effort to provide a level-appropriate study corpus for Lithuanian language learners. The collected corpus includes levelled texts from study books and unlevelled texts from other sources. The main goal is to assign the level-appropriate labels (A1, A2, B1, B2) to texts from other sources. For automatic classification we use preselected surface features, based on text readability research, and shallow linguistic features. First, we train the model with levelled texts from study books; second, we apply the learned model to classifying other texts. The best classification results are achieved with Logistic Regression method.