Task Overview
Slavic NLP 2027 hosts three shared tasks:
- Persuasion Techniques Detection & Classification (2nd edition): sentence-level detection and classification of persuasion techniques (25-technique taxonomy) in Bulgarian, Polish and Russian (to be extended), covering parliamentary debates and disinformation-related social media posts.
- Disinformation Detection: binary classification of texts as disinformation vs. non-disinformation in Polish, Slovak and Russian (to be extended), plus English data (MultiDis, MALINT). Co-organized with NASK National Research Institute.
- PolEval: the next edition of the Polish language processing and generation evaluation campaign, including a document layout recognition/classification task and further tasks to be announced.
See the Shared Tasks page for further details on each task.
Theme and Motivation
The Slavic languages play an important role due to their diverse cultural heritage and wide use — over 400M speakers worldwide. The current political and economic developments in Central/Eastern Europe have brought Slavic societies and their languages into focus, due to rapid technological advancement and expanding consumer markets. This workshop addresses Natural Language Processing (NLP) for the Slavic languages. The NLP tasks in urgent need of attention include morphological analysis, morphosyntactic tagging, syntactic parsing, lexical semantics, named entity recognition, text normalisation and non-standard language, reference resolution, information extraction, question answering, information retrieval, text summarization, machine translation, text classification, sentiment analysis, and linguistic resources.
Research on theoretical and applied topics in the context of Slavic languages is still underrepresented in the community. The linguistic phenomena specific to the Slavic languages — such as rich morphological inflection and free word order — make the construction of NLP tools for these languages a challenging and intriguing task.
The goal of this Workshop is to bring together researchers from academia and industry working on NLP for Slavic languages. In particular, the Workshop aims to stimulate research and foster the creation of tools and resources for these languages. The Workshop will provide a forum for exchanging ideas, discussing current problems, and making the available resources more widely known. One fascinating aspect of this language group is the striking structural similarity, as well as an easily recognizable core vocabulary and inflectional inventory spanning the entire group of languages — despite a lack of mutual intelligibility — which creates a special environment in which researchers can appreciate the shared problems and solutions, and communicate naturally. This Workshop continues the proud tradition established by the 9 previous Balto-Slavic Workshops.
This Workshop addresses Natural Language Processing (NLP) for the Slavic languages. The NLP tasks in urgent need of attention include:
- morphological analysis and generation
- morphosyntactic tagging
- syntactic and semantic parsing
- lexical semantics
- named-entity recognition
- text normalisation and processing non-standard language
- coreference resolution
- information extraction
- question answering
- information retrieval
- text summarization
- machine translation
- development of linguistic resources
- development and assessment of large language models
- disinformation detection
- fact verification
- text classification
- text generation
- sentiment analysis
Submission Guidelines
The workshop accepts long and short papers via OpenReview. Manuscripts can be submitted either directly or committed through ACL ARR. Shared task system description papers are submitted following the same process.
System Description Papers
Participating teams are invited to submit a system description paper to be published in the Slavic NLP 2027 Workshop proceedings, following the workshop's formatting and submission guidelines on OpenReview/ACL ARR.