CONFERENCE
On December 19, 2024, the seminar "Afternoon LATE: Conversations on the Latvian Language and Technologies" was held, which served as the final event of the National research program's "Latvian Studies for the Development of Latvian and European Society" project "Research on the Modern Latvian Language and the Development of Language Technologies" and the results of the project.
Project manager Ilze Auziņa introduced the audience to the team of the project, the main achievements of the research, and also emphasized that significant research on the phonetic, lexical and grammatical system has been initiated, which should be continued. Later she introduced the process of creating the "Modern Latvian Language Dictionary". Andra Kalnača presented in the presentation the research on word formation, semantics, pragmatics, etc. based on language data. Baiba Saulīte showed what syntactically marked data is available on Korpuss.lv and how to use it, furthermore she showed how and why the multi-word lexemes included in the “Thesaurus” are syntactically marked.
The event was attended by all project partners, as well as interested parties from the Ministry of Education and Science, the Latvian Language Agency, the Latvian Occupation Museum, the Latvian Union of the Deaf, the Latvian Council of Science, the Latvian Open Technology Association and other institutions.
About the project:
The institutions involved in the project are the University of Latvia (LU) Institute of Mathematics and Informatics, the LU Institute of the Latvian Language, the LU Faculty of Humanities, the LU Institute of Literature, Folklore and Art and the RTU Liepāja Academy (formerly – Liepāja University).
The project developed a digital infrastructure for language research, created new and supplemented existing language resources (corpora and dictionaries), which are included in the CLARIN-LV repository. More than 30 scientific publications have also been developed (25 of them indexed in the Web of Science and/or Scopus database), some of them are also included in the thematic collection of articles – Language: Meaning and Form 14. Grammar and Corpus Research. Kalnača, Andra (comp. and ed.). LU Academic Press, 2023. https://doi.org/10.22364/vnf.14. Almost 80 papers have been prepared on the research results and reported at 32 international scientific conferences.
The project was implemented in synergy with the National research program project “Development of an open and FAIR-compliant digital humanities ecosystem in Latvia (DHELI)” (VPP-IZM-DH-2022/1-0002) and “Language Technology Initiative” (2.3.1.1.i.0/1/22/I/CFLA/002) (VTI), but certain project directions will continue in the FLPP projects of the Science Council of Latvia, for example, “Development of computational lexical resources of the Latvian language for natural language understanding and text creation (WordNet2)” (lzp-2022/1-0443), “Database of morphemes and word formation models of the Latvian language” (LVMVMD) (lzp-2022/1-0013), “The most common errors in the Latvian language: corpus-based error analysis and text correction (Norma)” (lzp-2023/1-0481), “Standardization of Modern Latvian Language Spelling” (lzp-2024/1-0613).
