Clarin.si

The Slovene national consortium of the European research infrastructure @CLARINERIC, providing language resources and technologies, expertise and knowledge.

[Clarin.si @ClarinSlovenia]

Pridružite se Discord skupini slovenske skupnosti za jezikovne vire in tehnologije! Namenjena je sproščenemu pogovarjanju o izzivih, ugotovitvah in novostih s področij jezikovnih virov, tehnologij, korpusnega jezikoslovja in povezanih tem.

➡️https://t.co/RchH7lIQvX

[Clarin.si @ClarinSlovenia]

Vabljeni na predavanje JOTA društva SDJT, na katerem bo Miha Malenšek (UL FRI) predstavil domensko prilagajanje velikih jezikovnih modelov na področje prava v sklopu projekta LLM4DH.

📅 Sreda, 11. 3. 2026 ob 14:05
📍 UL FRI (Večna pot 113, Ljubljana), predavalnica P18

[Clarin.si @ClarinSlovenia]

📢 Call for Papers: Conference on Language Technologies & Digital Humanities (JT-DH 2026)

📍 17.–18. 9. 2026, in Ljubljana, Slovenia

Topics: NLP, language technologies, digital linguistics, DH

🗓 Submission deadline: 24. 4. 2026

Details & guidelines: https://t.co/d2J2IpY1yA

[Clarin.si @ClarinSlovenia]

Univerza na Primorskem vabi na predavanje "Kako učinkovito pripraviti načrt ravnanja z raziskovalnimi podatki", ki bo v četrtek, 5. 2. 2026, ob 11. uri.

ℹ️Dogodek bo potekal v slovenščini prek aplikacije Zoom.

➡️ Več informacij in prijava: https://t.co/c037el1XEF

[Taja Kuzman Pungeršek @TajaKuzman]

The CLASSLA-web 2.0 South Slavic web corpora are now available🥳

🔹 38M texts, 17B words
🔹 Linguistic annotations, genre & topic labels

🔗 Available on concordancers (https://t.co/2jqdWQYwIL) and for download (https://t.co/19r3DEdU2I)

📄 More info: https://t.co/RhI1DOSIQ8

[Clarin.si @ClarinSlovenia]

As we wrap up another eventful year, we would like to share an overview of the key developments and activities at our CLASSLA K-Centre during 2025, which includes new corpora, LLM benchmarks, workshops, and resources for SSH researchers.

➡️Read more here: https://t.co/zisZAKy6AF

[Clarin.si @ClarinSlovenia]

Our Knowledge Centre for South Slavic languages, CLASSLA, wishes you cheerful holidays and a successful start to 2026!

We look forward to sharing our expertise and services for South Slavic languages even further across Europe and beyond, and to even more collaboration in 2026.

[Clarin.si @ClarinSlovenia]

As 2025 ends, we are happy to present a short video on the use of the https://t.co/X31izGUVD6 website, repository, and concordancers this year. Thank you to all team members, collaborators, and users who have contributed to our infrastructure. Wishing you a joyful 2026!

[Clarin.si @ClarinSlovenia]

We are happy to share the Call for Papers for the First Workshop on Creating Interoperable Corpora of Historical Newspapers at the LREC 2026 conference:
📅16 May 2026
📍Palma de Mallorca, Spain
❗Submission Deadline: 1 March 2026
➡️ More information: https://t.co/RB4dEElz0T

[Clarin.si @ClarinSlovenia]

📢 Deadline Extended: https://t.co/X31izGUVD6 Survey

If you haven’t yet completed the survey on the services, resources, and tools provided by https://t.co/X31izGUVD6, there is still time to contribute (until December 10th)!

➡️Take the survey here: https://t.co/8Dewe8Yzii

[Clarin.si @ClarinSlovenia]

We invite you to participate in a survey that will help us evaluate and plan the development of our services, activities, resources, and tools.

🙏Take the 15-minute anonymous survey (English version): https://t.co/8Dewe8Yzii

The survey is open until the end of November.

[Clarin.si @ClarinSlovenia]

Vabljeni na predavanje JOTA društva SDJT, na katerem bo Tomaž Savodnik (Zavod za informacijsko družbo) predstavil svoje izkušnje pri prilagajanju velikih jezikovnih modelov za slovenščino.

📅 četrtek, 27. 11. 2025 ob 13h
📍 UL FRI (Večna pot 113, Ljubljana) v predavalnici P04

[Clarin.si @ClarinSlovenia]

We invite you to participate in a survey that will help us evaluate and plan the development of our services, activities, resources, and tools.

🙏Take the 15-minute anonymous survey (English version): https://t.co/8Dewe8Yzii

The survey is open until the end of November.

[Clarin.si @ClarinSlovenia]

⚠️ Due to scheduled maintenance, the https://t.co/X31izGUnNy services will be temporarily unavailable from this Friday afternoon until this Saturday evening (7 to 8 November 2025).

We apologise for any inconvenience and thank you for your understanding and patience.

[Clarin.si @ClarinSlovenia]

Vabljeni na predavanje JOTA društva SDJT, na katerem bosta Alenka Unk (Generalni direktorat za prevajanje) in Peter Jakša (Območna enota Generalnega direktorata za prevajanje) predstavila storitve UI iz Evropske komisije.
🗓️torek, 11. 11. 2025 ob 13:05
📍UL FRI, predavalnica P03

[Clarin.si @ClarinSlovenia]

We are happy to add that the Global PIQA includes a series of South Slavic languages as well, including Slovenian, Slovenian Cerkno dialect, Croatian, Croatian Chakavian dialect, Serbian, Macedonian, Bosnian and Bulgarian😃
Read more : https://t.co/15U9urrWBy

[Multilingual Representation Workshop @ EMNLP 2026 @mrl_workshop]

Introducing Global PIQA, a new multilingual benchmark for 100+ languages. This benchmark is the outcome of this year’s MRL shared task, in collaboration with 300+ researchers from 65 countries. This dataset evaluates physical commonsense reasoning in culturally relevant contexts.

[Clarin.si @ClarinSlovenia]

⚠️ Due to scheduled maintenance, the https://t.co/X31izGUVD6 services will be temporarily unavailable on Friday, 26 September 2025, approximately between 13:00 and 21:00.

We apologise for any inconvenience and thank you for your understanding and patience.

[Clarin.si @ClarinSlovenia]

⚡ Reminder: CLASSLA-Express in Graz!
Explore corpus-linguistic research with South Slavic web corpora, concordancers and AI:
📅 10. 10. 2025, 11:00 - 18:00
📍 Institute for Slavic Studies, University of Graz, Austria

Registration and programme at:
https://t.co/nHQdBLG9D0

[Clarin.si @ClarinSlovenia]

ParlaMint 5.0 is out - now with CAP topic labels and sentiment annotations🥳! The corpus collection is available in three versions (original, linguistically annotated, and machine-translated to English) on our repository and concordancers.
➡️See more: https://t.co/d3AUquNJQL

[Clarin.si @ClarinSlovenia]

🖋️ Reporting from the first stop of CLASSLA-Express 2.0: Corpora vs. Large Language Models😃:
- talks on web corpora, LLMs, and AI tools in phraseology;
- a hands-on session exploring synergies between LLMs and corpus linguistics methods.

➡️Read more: https://t.co/fzSUTOCVkF

[Clarin.si @ClarinSlovenia]

Join the SyntaxFest 2025 bringing together 5 conferences (IWPT, UDW, TLT, DepLing, QUASY) and 2 UniDive workshops focused on empirical syntax and NLP!

📍 Ljubljana, Slovenia
🗓️August 26–29, 2025

❗️ Early bird registration open until July 15
➡️ Details: https://t.co/WU7LMd3km5

[Clarin.si @ClarinSlovenia]

Vabljeni na predavanje JOTA društva SDJT, na katerem bo Andrija Poleksić (Univerza v Reki) predstavil podatkovno usmerjen pristop vzpostavljanja sistemov znanja za raziskovanje podnebnih sprememb.

📅 sreda, 9. julij 2025, ob 16:00
📍 UL FRI, predavalnica P21