fortvivlan's picture
Model save
4439dd7 verified
metadata
base_model: xlm-roberta-base
datasets: CoBaLD/enhanced-cobald
language: en
library_name: transformers
license: gpl-3.0
metrics:
  - accuracy
  - f1
pipeline_tag: token-classification
tags:
  - pytorch
model-index:
  - name: CoBaLD/xlm-roberta-base-cobald-parser
    results:
      - task:
          type: token-classification
        dataset:
          name: enhanced-cobald
          type: CoBaLD/enhanced-cobald
          split: validation
        metrics:
          - type: f1
            value: 0.9257791579861928
            name: Null F1
          - type: f1
            value: 0.7644881331868549
            name: Lemma F1
          - type: f1
            value: 0.7691162750186747
            name: Morphology F1
          - type: accuracy
            value: 0.8559278875534733
            name: Ud Jaccard
          - type: accuracy
            value: 0.7969800122196037
            name: Eud Jaccard
          - type: f1
            value: 0.9984168766518762
            name: Miscs F1
          - type: f1
            value: 0.6020538395167092
            name: Deepslot F1
          - type: f1
            value: 0.5911474360181621
            name: Semclass F1

Model Card for xlm-roberta-base-cobald-parser

A transformer-based multihead parser for CoBaLD annotation.

This model parses a pre-tokenized CoNLL-U text and jointly labels each token with three tiers of tags:

  • Grammatical tags (lemma, UPOS, XPOS, morphological features),
  • Syntactic tags (basic and enhanced Universal Dependencies),
  • Semantic tags (deep slot and semantic class).

Model Sources

Citation

@inproceedings{baiuk2025cobald,
  title={CoBaLD Parser: Joint Morphosyntactic and Semantic Annotation},
  author={Baiuk, Ilia and Baiuk, Alexandra and Petrova, Maria},
  booktitle={Proceedings of the International Conference "Dialogue"},
  volume={I},
  year={2025}
}