Ninth Workshop on Universal Dependencies (UDW 2026)
May 2026, Palma de Mallorca, Spain (co-located with LREC 2026)

Universal Dependencies (UD) is a framework for cross-linguistically consistent treebank annotation that has so far been applied to over 180 languages. The framework aims to capture similarities as well as idiosyncrasies among typologically different languages (e.g., morphologically rich languages, pro-drop languages, and languages featuring clitic doubling). The goal in developing UD was not only to support comparative evaluation and cross-lingual learning but also to facilitate multilingual natural language processing, enable comparative linguistic studies, and provide resources for language model understanding and evaluation.

The Universal Dependencies Workshop series was started to create a forum for discussion of the theory and practice of UD, its use in research and development, and its future goals and challenges. Some of the previous workshops have been co-located with COLING, EMNLP, and SyntaxFest. We invite papers on all topics relevant to UD, including but not limited to:

  • Theoretical foundations and universal guidelines
  • Linguistic analysis of specific languages and/or constructions
  • Language typology and linguistic universals
  • Treebank annotation, conversion, and validation
  • Word segmentation, morphological tagging and syntactic parsing
  • Use of UD data for evaluating or understanding language models
  • Linguistic studies based on the UD data

Priority will be given to papers that adopt a cross-lingual perspective.

Important Dates

  • Paper submission deadline: February 16, 2026
  • Notification of acceptance: March 16, 2026
  • Camera-ready version due: March 30, 2026
  • Conference dates: May 11-16, 2026

We invite submissions in two formats:

  • Regular (long) papers up to 8 pages of content (excluding references and appendices). Regular papers should present substantial, original, and unpublished research, including empirical evaluation results where appropriate.
  • Short papers up to 4 pages of content (excluding references and appendices). Short papers may offer smaller, focused contributions, such as work in progress, negative results, surveys, or opinion pieces.

We also welcome non-archival papers, defined as work that has already been published or accepted for publication at another computational linguistics venue. These papers may be presented at the workshop but will not appear in the LREC 2026 Workshop Proceedings.

Accepted papers will be given one additional page to address reviewer comments.

Paper Submission, Review Process and Selection Criteria

Submissions will be handled via the START Conference Manager. The submission link will be provided on the workshop website as soon as it becomes available. Papers should describe original work; they should emphasise completed work rather than intended work, and should indicate clearly the state of completion of the reported results. Submissions will be judged on correctness, originality, technical strength, significance and relevance to the conference, and interest to the attendees.

All papers will undergo a double-blind peer review process, with final acceptance decisions made by the workshop chairs. Submissions that violate the requirements above will be rejected without review.

All submissions should follow the two-column LREC style guidelines. We strongly recommend the use of the LaTeX style files, OpenDocument, or Microsoft Word templates created for LREC: https://lrec2026.info/authors-kit/. All papers must be anonymous, i.e., not reveal author(s) on the title page or through self-references. So, e.g., “We previously showed (Smith, 2020) …”, should be avoided. Instead, use citations such as “Smith (2020) previously showed …”.

LRE-Map and Sharing Language Resources

When submitting a paper from the START page, authors will be asked to provide essential information about resources (in a broad sense, i.e. also technologies, standards, evaluation kits, etc.) that have been used for the work described in the paper or are a new result of your research. Moreover, ELRA encourages all LREC authors to share the described LRs (data, tools, services, etc.) to enable their reuse and replicability of experiments (including evaluation ones).

Presentation Format

Accepted papers will be presented as oral or poster presentations. The mode of presentation will be determined by the workshop chairs and does not reflect the quality of the submission.

Accepted papers will be published in the LREC 2026 Workshop Proceedings.