Please use the following text to cite this item or export to a predefined format:
Straka, Milan, 2026,
CRAC 2026 Empty Nodes Baseline Model, LINDAT/CLARIAH-CZ digital library at the Institute of Formal and Applied Linguistics (ÚFAL),
http://hdl.handle.net/11234/1-6081.
| dc.contributor.author | Straka, Milan |
| dc.date.accessioned | 2026-01-30T20:53:08Z |
| dc.date.available | 2026-01-30T20:53:08Z |
| dc.date.issued | 2026-01-30 |
| dc.description | The crac2026_empty_nodes_baseline is a XLM-RoBERTa-large–based multilingual model for CRAC 2026 Empty Nodes Baseline system https://github.com/ufal/crac2026_empty_nodes_baseline for predicting empty nodes in the input CoNLL-U files, trained on CorefUD 1.4 data. It was was used to generate baseline empty nodes prediction in the CRAC 2026 Shared Task on Multilingual Coreference Resolution https://ufal.mff.cuni.cz/corefud/crac26. The model is language agnostic, so in theory it can be used to predict coreference in any XLM-RoBERTa language. Compared to the last year CRAC 2025 Empty Nodes Baseline https://github.com/ufal/crac2025_empty_nodes_baseline, this year's baseline predicts all available information for the empty nodes, i.e., including forms, lemmas, UPOS, XPOS, and FEATS columns, in addition to previously predicted word order and dependency relations of the empty nodes. Instructions for running prediction, training, and intrinsic evaluation are all available in the repository CRAC 2026 Empty Nodes Baseline https://github.com/ufal/crac2026_empty_nodes_baseline. |
| dc.identifier.uri | http://hdl.handle.net/11234/1-6081 |
| dc.language.iso | cat |
| dc.language.iso | ces |
| dc.language.iso | chu |
| dc.language.iso | spa |
| dc.language.iso | grc |
| dc.language.iso | hun |
| dc.language.iso | pol |
| dc.language.iso | tur |
| dc.publisher | Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL) |
| dc.rights | Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) |
| dc.rights.label | PUB |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-sa/4.0/ |
| dc.source.uri | https://github.com/ufal/crac2026_empty_nodes_baseline |
| dc.subject | CRAC shared task |
| dc.subject | CRAC 2026 |
| dc.subject | CorefUD |
| dc.subject | CorefUD 1.4 |
| dc.subject | Empty nodes |
| dc.title | CRAC 2026 Empty Nodes Baseline Model |
| dc.type | toolService |
| local.contact.person | Milan Straka straka@ufal.mff.cuni.cz Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL) |
| local.files.count | 1 |
| local.files.size | 2327591758 |
| local.has.files | yes |
| local.language.name | Catalan |
| local.language.name | Czech |
| local.language.name | ChurchSlavic |
| local.language.name | Spanish |
| local.language.name | AncientGreek (to 1453) |
| local.language.name | Hungarian |
| local.language.name | Polish |
| local.language.name | Turkish |
| local.sponsor | nationalFunds CZ.02.01.01/00/23_020/0008518 Ministerstvo školství, mládeže a tělovýchovy České republiky Jazykověda, umělá inteligence a jazykové a řečové technologie: od výzkumu k aplikacím |
| metashare.ResourceInfo#ContentInfo.detailedType | tool |
| metashare.ResourceInfo#ResourceComponentType#ToolServiceInfo.languageDependent | true |
Collections
This item isPublicly Available
and licensed under:
Files in this item
- Name
- crac2026_empty_nodes_baseline.zip
- Size
- 2.17 GB
- Format
- application/zip
- Description
- CRAC 2026 Empty Nodes Baseline Model
- MD5
- bd978678d6864dccd146d8f7ff361446

- crac2026_empty_nodes_baseline
- README.md6 kB
- options.json1 kB
- mappings.json24 kB
- LICENSE.txt20 kB
- model.weights.pt2 GB
- crac2026_empty_nodes_baseline
- README.md6 kB
- options.json1 kB
- mappings.json24 kB
- LICENSE.txt20 kB
- model.weights.pt2 GB

