First Shared Task on UMR Parsing

Jan Štěpánek, Daniel Zeman, Marketa Lopatkova, Federica Gamba, Hana Hledíková, Nianwen Xue


Abstract
The paper presents the first shared task on parsing Uniform Meaning Representation (UMR), a graph-based framework for cross-linguistic semantic annotation of typologically diverse languages. The task requires systems to enrich plain text with sentence-level structure, node–token alignment, and document-level relations. It involves processing data for seven languages from four language families (Indo-European, Sino-Tibetan, Na-Dene, and Algic). Six languages have at least some training data; for one language, data is not available, leading to a zero-shot scenario. The training dataset as well as the gold-standard test set for all seven languages is released and made available for follow-up research. We present the task setup and evaluation methodology, using two graph matching approaches – a traditional, and an alignment-sensitive one, tailored specifically for UMR. Two participating systems are compared, each representing different modeling approaches. Results highlight the challenges of UMR parsing, particularly for alignment prediction and document-level semantics, and reveal substantial variation across languages and annotation conditions.
Anthology ID:
2026.dmr-1.12
Volume:
Proceedings of The Seventh International Workshop on Designing Meaning Representations (DMR 2026) @ LREC 2026
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Jin Zhao, Claire Benet Post, Elizabeth Hoefer
Venues:
DMR | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
136–147
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-dmr-12
DOI:
10.63317/3taoes4u6cmk
Bibkey:
Cite (ACL):
Jan Štěpánek, Daniel Zeman, Marketa Lopatkova, Federica Gamba, Hana Hledíková, and Nianwen Xue. 2026. First Shared Task on UMR Parsing. In Proceedings of The Seventh International Workshop on Designing Meaning Representations (DMR 2026) @ LREC 2026, pages 136–147, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
First Shared Task on UMR Parsing (Štěpánek et al., DMR 2026)
Copy Citation: