Corpus Based Self-Assessment Platform for Latvian Language Learners

Roberts Darģis, Ilze Auziņa, Inga Kaija, Kristīne Levāne-Petrova, Kristīne Pokratniece

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)
2 Downloads (Pure)


This paper presents a self-assessment platform for Latvian language learners in the breakthrough (A1) and Waystage (A2) levels. The self-assessment platform contains three types of exercises (typing, inflection and gap filling) based on error analysis of the Latvian Language Learner corpus (LaVA). All exercises are automatically generated based on data from multiple corpora. The automatically generated exercises are useful not only for learners outside of classroom or even outside of any formal education setting, but also for educators and authors of learning aids. Currently the self-assessment platform is tailored for language learners at the beginner level, but it can be easily extended for more advanced levels. The self-assessment platform is freely available online ( and the interface is translated in two language – Latvian and English.

Original languageEnglish
Pages (from-to)392-401
Number of pages10
JournalBaltic Journal of Modern Computing
Issue number3
Publication statusPublished - 2022


  • Acquisition
  • Computer-Assisted Language Learning (CALL)
  • Latvian

Field of Science*

  • 1.2 Computer and information sciences
  • 5.3 Educational sciences
  • 6.2 Languages and Literature

Publication Type*

  • 1.1. Scientific article indexed in Web of Science and/or Scopus database


Dive into the research topics of 'Corpus Based Self-Assessment Platform for Latvian Language Learners'. Together they form a unique fingerprint.

Cite this