| Full name | CLARIN Knowledge Centre for Croatian Language |
| Short name | CROATINA |
| URL | https://www.clarin.hr/en/centres |
| Hosted by | (1) Institute of Linguistics, Faculty of Humanities and Social Sciences (FFZG), University of Zagreb, Croatia
(2) Institute of Croatian Language and Linguistics (IHJJ), University of Zagreb, Croatia |
| City of main hub | Zagreb |
| Country of main hub | HR |
| Active since | 2023-10-30 |
| Area of competence | The CLARIN Knowledge Centre for Croatian language (CROATINA) provides relevant knowledge about Croatian language and promotes the use of language technologies. CROATINA Helpdesk is a service offering information about the variety of topics related to Croatian language, Croatian language learning and use of language resources. CROATINA also offers help in depositing language resources in HR-CLARIN or other repositories. While the existing K-centre CLASSLA is oriented primarily towards the language resources for all South-Slavic languages, CROATINA will offer complementary language resources specific for Croatian only. Additionally, through FAQ and helpdesk CROATINA will cover relevant linguistic information about the Croatian language, its history, structure at all language levels, typological features, sociolinguistic environment, level of the language technological support, and other linguistically and technologically relevant information. Following their research interests and different language resources two K-centres offer, the users should be able to select the relevant K-centre by themselves, or they could approach CROATINA for additional guidance. |
| Audiences | - Linguists
- Computational linguists
- Language teachers
- Digital humanists
- Language technology developers
- Students
- Researchers in information and communication sciences |
| Types of services | - Access to data
- Access to tools
- Depositing
- User assistance
- FAQ
- Helpdesk
- Video lectures
- Training courses |
| Language portal for | - Croatian language (ISO 639-3: hrv, glottolog: croa1245) in all its varieties; e.g. including
- Kajkavian dialect (ISO 639-3: kjv; glottolog: kajk1237),
- Chakavian dialect (glottolog: chak1265),
- Burgenland Croatian dialect (glottolog: 1244),
- Croatian Molisano/Slavomolisano dialect (glottolog: slav1254), etc. |
| Other languages covered | |
| Modalities covered | - Written text primarily
- Spoken and multimodal language resources are planned in the longer term. |
| Linguistic topics | - Phonology
- Morphology
- Syntax
- Semantics
- Pragmatics
- Discourse
- Corpus linguistics
- Language resources
- Language technology
- Lexicography |
| Language processing topics | - Tokenisation
- PoS/MSD tagging
- Lemmatisation
- Named entity recognition
- Corpora creation and management
- Lexica creation and management
- Morphological processing at inflectional and derivational level
- Multimodal annotations
- Parsing (syntactic and semantic)
- Language models
- Croatian language processing |
| Data types | - Monolingual corpora
- Parallel corpora
- Wordnets
- Treebanks
- Language models
- Morphology databases
- Lexica |
| Resource families | - Computer-mediated communication corpora (social media)
- Corpora of academic texts
- Historical corpora
- L2 learner corpora
- Legal corpora
- Literary corpora
- Manually annotated corpora
- Multimodal corpora
- Newspaper corpora
- Oral history corpora
- Parallel corpora
- Reference corpora
- Spoken corpora
- Conceptual resources
- Dictionaries
- Glossaries
- Language models
- Lexica
- Wordlists
- Normalisation
- Named entity recognition
- Part-of-speech tagging and lemmatisation
- Tools for sentiment analysis |
| Generic topics | - Data management
- Metadata
- Language Technology platforms and frameworks
- Grammars |
| Other keywords | - Expertise in CALL for Croatian as L2 (incl. L2 corpora)
- Expertise in language processing chain for Croatian based on LLM(s) (incl. POS-tagging and lemmatisation) |
| Tour de CLARIN introduction | |
| Tour de CLARIN interview | |
| Last update | 2024-04-26 15:33:52 |