LLMs4SSH – CLARIN K-centre for Large Language Models in SS&H
What is LLMs4SSH?
The Centre is a centre of expertise, skills and technological resources offering advice on various applications of LLMs in processing language data and on expansion and adaptation of LLMs to the needs of SS&H researchers and their tasks. The Centre will also offer help in finding and selecting LLMs appropriate for the needs of researchers, support users in accessing computational resources , as well as, collect and share knowledge about the existing LLMs
What do we do to support our users?
- We advise how to make use of Large Language Models in research
- We help in the preparation of grant proposals which assume the use of LLMs in research
- We train in the scope of using LLMs in research in SS&H
Who are the target users of the LLMs4SSH?
- linguists
- computational linguists
- economists
- sociologists
- psychologists
- media researchers
- researchers of communication
- literature researchers
- students writing diploma theses (bachelor's, master's, doctoral)
Which are the aspects of LLMs4SSH expertise?
- natural language preprocessing (lemmatisation, morphosyntactic analysis, parsing)
- stylometric research
- lexico-semantic analysis
- Distributional Semantics and its applications
- speech recognition
- named entity recognition
- temporal expression recognition
- creating and managing text corpora
- parallel corpora
- wordnet building and use
- data mining
- information extraction from texts
- text statistics preparation
- semantic text classification
- extraction of meta-data from text
- word sense disambiguation
Which are the participating institutions?
- CLARIN‑PL
- LINDAT/CLARIAH‑CZ
- CLARIN‑LV
- PORTULAN CLARIN
- CLARIN‑NL and CLARIN‑BE
- CLARIN‑EL
- FIN‑CLARIN
- CLARIAH‑ES
- HUN‑REN
- HR‑CLARIN
- CLARIN‑CH
- CLARIN.SI
- CLaDA‑BG
Find out more about the centre
Visit the official web site.