About HiČKoK

The HiČKoK project aims create data, software and knowledge resources for the study of Czech across its history (from the 13th to the 21st century). The project is unique in that it attempts for the first time ever to connect the individual centers where text corpora for different phases of Czech language history have been independently built, and by merging their resources to create a unique tool for the study of language development.

The second ambitious goal of the project is to create tools for unified morphological and syntactic annotation of Czech across all periods within the Universal dependencies (UD) scheme.

Planned project outcomes

Implementation of the HiČKoK project should result in compiling and providing access to:

• a Monitor corpus covering all developmental stages in the history of Czech
• language models in the Universal Dependencies (UD) scheme, for automatic linguistic annotation of texts from any time period
• an application allowing to study diachronic phenomena in the Monitor corpus
• an online course for students and researchers working with historical texts, covering the outputs of the project and other relevant technologies available within the project consortium.

Research team

Project consortium

• Institute of the Czech National Corpus, FF UK (Project administrator)
• Czech Language Institute, AV ČR
• Institute of Formal and Applied Linguistics, MFF UK
• National Library of the Czech Republic

Grant support

The HiČKoK project (No. TQ01000072) was supported by the Technology Agency of the Czech Republic for the period 09/2023 – 11/2026 within the framework of the SIGMA program for the support of applied research and innovation.

Outputs

Martin Stluka, Václav Cvrček: HiČKoK: historie češtiny v korpusovém kontinuu (29. 4. 2024). Lecture recording, Odborné fórum ÚISK FF UK