Skip to main navigation Skip to search Skip to main content

User-friendly Search Possibilities for Early Latvian Texts: Challenges Posed by Automatic Conversion

  • University of Latvia

Research output: Chapter in Book/Report/Conference proceedingConference paperResearchpeer-review

2 Citations (Scopus)

Abstract

This paper deals with the Corpus of early written Latvian and explains the methodology for normalising historical spellings found in texts from the 16th-18th cc. It describes the types of replacements which will make searching early texts more convenient.

Original languageEnglish
Title of host publicationCEUR Workshop Proceedings
Pages168-176
Number of pages9
Volume3232
Publication statusPublished - 2022

Publication series

NameCEUR Workshop Proceedings
PublisherCEUR-WS
ISSN (Print)1613-0073

Keywords

  • conversion of old spelling into modern
  • Historical corpus
  • replacement algorithms

OECD Field of Science

  • 1.2 Computer and Information Sciences

Fingerprint

Dive into the research topics of 'User-friendly Search Possibilities for Early Latvian Texts: Challenges Posed by Automatic Conversion'. Together they form a unique fingerprint.

Cite this