| Full name | CLARIN Knowledge Centre for South Slavic languages |
| Short name | CLASSLA |
| URL | http://www.clarin.si/info/k-centre/ |
| Hosted by | (1) Jožef Stefan Institute (CLARIN.SI), Ljubljana, Slovenia
(2) Institute of Croatian Language (IHJ), Zagreb, Croatia
(3) Institute of Information and Communication Technologies (CLADA-BG), Sofia, Bulgaria |
| City of main hub | Ljubljana |
| Country of main hub | SI |
| Active since | 2019-03-19 |
| Area of competence | CLASSLA offers expertise on language resources and technologies for South Slavic languages. It provides information on freely available lexicons and corpora, which can be used in research in the social sciences and humanities. The CLASSLA-Stanza pipeline allows researchers to perform language processing of their texts to produce their own corpora, while the CLASSLA web corpora as the largest general corpora for all South Slavic languages enable direct language research. The centre provides guidance in how to use the available resources and technologies in research. |
| Audiences | - Computational linguists
- Computer scientists
- Citizen scientists
- Historians
- Language teachers
- Linguists
- Sociolinguists
- Sociologists |
| Types of services | - FAQ
- Helpdesk
- Technical support
- Training |
| Language portal for | - Slovenian
- Slovene
- Croatian
- Bosnian
- Serbian
- Montenegrin
- Macedonian
- Bulgarian |
| Other languages covered | |
| Modalities covered | - Audio: speech
- Text |
| Linguistic topics | - Applied linguistics
- Dialect studies
- Sociolinguistics |
| Language processing topics | - Basic language processing
- Information extraction
- Language understanding
- Named entity recognition
- Processing of morphologically rich languages
- Speech recognition |
| Data types | - Manually annotated datasets
- Corpora
- Language models
- Treebanks |
| Resource families | - Computer-mediated communication corpora (social media)
- Historical corpora
- Literary corpora
- Newspaper corpora
- Parliamentary corpora
- Corpora of academic texts
- Manually annotated corpora
- Multimodal corpora
- Parallel corpora
- Reference corpora
- Spoken corpora
- Language models
- Lexica
- Normalization
- Named entity recognition
- Part-of-speech tagging and lemmatization
- Tools for sentiment analysis |
| Generic topics | - Evaluation of tools and models
- Machine learning
- Deep learning |
| Other keywords | - Processing of closely related languages
- Language variation
- Spatial language variation |
| Tour de CLARIN introduction | https://www.clarin.eu/blog/tour-de-clarin-clarin-knowledge-centre-south-slavic-languages-classla |
| Tour de CLARIN interview | https://www.clarin.eu/blog/tour-de-clarin-interview-zrinka-kolakovic |
| Last update | 2024-07-22 10:43:42 |