About the Workshop
Slavic languages play a crucial role in Natural Language Processing (NLP) due to their diverse cultural heritage and wide use — over 400M speakers worldwide. Slavic NLP 2027 addresses NLP tasks in urgent need of attention, including persuasion techniques detection, disinformation detection, and PolEval - Polish Evaluation Campaign with four different shared tasks.
The SlavicNLP 2027 Workshop programme features oral presentations of long and short an invited talk by a researcher in Slavic NLP, a session dedicated to the Shared Tasks (including system description papers), and a poster session.
Shared Tasks at Slavic NLP 2027
Persuasion Techniques Detection & Classification (2nd edition)
Detection and classification of persuasion techniques at the sentence level in Bulgarian, Polish and Russian, covering parliamentary debates and disinformation-related social media posts, using a taxonomy of 25 persuasion techniques.
Disinformation Detection
Binary classification of texts as disinformation vs. non-disinformation in Polish, Slovak and Russian, plus English data.
PolEval
The next edition of the long-running Polish language evaluation campaign, including a task on recognition and classification of document layout elements from page images.
Invited Speaker
Wojciech Kusa
Head of the NLP Department at NASK National Research Institute, Warsaw, Poland. The keynote will focus on the challenges and experiences in developing PLLuM, an open Polish Large Language Model.
News
| Date | Announcement |
|---|---|
| 2026-10-02 | The SlavicNLP Workshop has been accepted at EACL 2027 in Athens. |
| 2026-09-20 | Website launched with details on the three Slavic NLP 2027 shared tasks: Persuasion Techniques, Disinformation Detection, and PolEval. |
Sponsorship
Slavic NLP 2027 is sponsored by SIGSLAV — the ACL Special Interest Group on NLP for Slavic Languages.