multiclinner_enigma_cz_disease_robeczech-para
Czech clinical Named Entity Recognition model for the
DISEASE entity
type, fine-tuned from
ufal/robeczech-base on the
Czech portion of the
MultiClinAI 2026 IberLEF shared task.
Developed by
Team Enigma at the Faculty of Mathematics and Informatics,
Sofia University.
Summary
| |
|---|
| Task | Token classification (BIO), single entity type |
| Entity type | DISEASE (diseases and disorders) |
| Language | Czech (cs) |
| Base model | ufal/robeczech-base |
| Architecture | Transformer (softmax) |
| Augmentation | Morphological synonyms + GPT-4.1-mini paraphrase |
| Training data | MultiClinAI Czech train + dev combined (1,258 documents) plus augmentation |
| Test F1 (strict) | 0.6494 (char F1 0.7710) |
Quick start
1from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
2
3repo = "SU-FMI-AI/multiclinner_enigma_cz_disease_robeczech-para"
4
5tokenizer = AutoTokenizer.from_pretrained(repo)
6model = AutoModelForTokenClassification.from_pretrained(repo)
7
8ner = pipeline(
9 "token-classification",
10 model=model,
11 tokenizer=tokenizer,
12 aggregation_strategy="simple",
13)
14
15text = "Pacient byl přijat s hypertenzí a podstoupil koronarografii."
16for span in ner(text):
17 print(span)
Each predicted span is a dictionary with keys entity_group,
score, word, start, end.
Label set
The model predicts a single entity type using the BIO tagging scheme:
| ID | Label | Meaning |
|---|
| 0 | O | outside any entity |
| 1 | B-DISEASE | beginning of a DISEASE mention |
| 2 | I-DISEASE | inside a DISEASE mention |
Intended use
- Extracting
DISEASE mentions from Czech clinical text (discharge
summaries, case reports, medical records).
- Building block for ensembles (this model was deployed as part of an
ensemble in the original submission).
- A starting point for further fine-tuning on related Czech biomedical
corpora.
Out-of-scope use
- Other languages. Although the XLM-RoBERTa based variants share a
multilingual encoder, the classification head was only trained on Czech.
- Other domains. The model was not exposed to non-clinical text, social
media or layperson descriptions.
- Clinical decision making. This is a research artifact. Do not use it
as the sole input to any clinical decision.
Training data
- Source. MultiClinAI Czech NER: 1,006 train documents
and 252 dev documents per entity type in BRAT standoff format, derived
from the DisTEMIST, SympTEMIST and MedProcNER corpora translated and
annotation-projected to Czech. For the final submission models the gold
train + dev sets are merged into a single training partition (no
held-out validation).
- Augmentation. Morphological synonym replacement + LLM paraphrase augmentation. Morphological augmentation as described above, plus a paraphrase set generated with
GPT-4.1-mini: each clinical sentence is rewritten so the surface form changes while the gold entity character spans are preserved and re-projected onto the new text.
- Tokenisation. SentencePiece tokenizer inherited from the base model.
Training procedure
| Hyperparameter | Value |
|---|
| Base model | ufal/robeczech-base |
| Head | SOFTMAX |
| Optimiser | AdamW |
| Learning rate | 2e-5 |
| Batch size | 64 |
| Epochs | 10 |
| Max sequence length | 512 |
| Input granularity | Sentence-level |
| Warmup ratio | 0.1 |
| Weight decay | 0.01 |
| Seed | 42 |
| Mixed precision | fp16 (CUDA) |
Token classification head: backbone hidden states are projected through a linear layer to BIO logits and decoded greedily (argmax per token).
Evaluation
Held-out development set
Best dev-set entity-level F1 observed during development: 0.703.
MultiClinAI Czech, official blind test set
Run name in the official MultiClinAI ranking: robeczech-para_cz_disease.
| Metric | Strict | Character-level |
|---|
| Precision | 0.6671 | 0.7931 |
| Recall | 0.6325 | 0.7500 |
| F1 | 0.6494 | 0.7710 |
Strict matching requires the predicted span to exactly match a gold span
(same start, end, and type). Character-level matching gives partial credit
for overlapping spans.
Related models
Other models for the same entity type:
SU-FMI-AI/multiclinner_enigma_cz_disease_robeczech-morph: robeczech-base, Morphological synonyms (curated + Wikidata), SOFTMAX head, test F1 = 0.6552.SU-FMI-AI/multiclinner_enigma_cz_disease_xlmr-crf: xlm-roberta-base, Morphological synonyms (curated + Wikidata), CRF head, test F1 = 0.6381.SU-FMI-AI/multiclinner_enigma_cz_disease_xlmr-para: xlm-roberta-base, Morphological synonyms + GPT-4.1-mini paraphrase, SOFTMAX head, test F1 = 0.6283.SU-FMI-AI/multiclinner_enigma_cz_disease_xlmr-os1: xlm-roberta-base, Morphological synonyms + 1x oversample of entity-bearing docs, SOFTMAX head, test F1 = 0.6440.
License
Released under the
apache-2.0
license. Base-model and dataset licenses apply to their respective
artifacts.
Code and resources
Training code, augmentation pipeline, ablation log and evaluation scripts
are available in the project's GitHub repository:
https://github.com/TeogopK/MultiClinAI-Czech.
