README.md

metadata

datasets:
  - bc5cdr
metrics:
  - f1
  - precision
  - recall
model-index:
  - name: tner/deberta-v3-large-bc5cdr
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: bc5cdr
          type: bc5cdr
          args: bc5cdr
        metrics:
          - name: F1
            type: f1
            value: 0.8902493653874869
          - name: Precision
            type: precision
            value: 0.8697724178175452
          - name: Recall
            type: recall
            value: 0.9117137322866755
          - name: F1 (macro)
            type: f1_macro
            value: 0.8863403908610603
          - name: Precision (macro)
            type: precision_macro
            value: 0.8657302393432342
          - name: Recall (macro)
            type: recall_macro
            value: 0.9080747413030301
          - name: F1 (entity span)
            type: f1_entity_span
            value: 0.8929371360310587
          - name: Precision (entity span)
            type: precision_entity_span
            value: 0.8723983660766388
          - name: Recall (entity span)
            type: recall_entity_span
            value: 0.9144663064532572
pipeline_tag: token-classification
widget:
  - text: Jacob Collier is a Grammy awarded artist from England.
    example_title: NER Example 1

tner/deberta-v3-large-bc5cdr

This model is a fine-tuned version of microsoft/deberta-v3-large on the tner/bc5cdr dataset. Model fine-tuning is done via T-NER's hyper-parameter search (see the repository for more detail). It achieves the following results on the test set:

• F1 (micro): 0.8902493653874869
• Precision (micro): 0.8697724178175452
• Recall (micro): 0.9117137322866755
• F1 (macro): 0.8863403908610603
• Precision (macro): 0.8657302393432342
• Recall (macro): 0.9080747413030301

The per-entity breakdown of the F1 score on the test set are below:

• chemical: 0.9298502009499452
• disease: 0.8428305807721753

For F1 scores, the confidence interval is obtained by bootstrap as below:

• F1 (micro):
  • 90%: [0.885162383660078, 0.8951239957151518]
  • 95%: [0.8838793313408008, 0.8959517574197015]
• F1 (macro):
  • 90%: [0.885162383660078, 0.8951239957151518]
  • 95%: [0.8838793313408008, 0.8959517574197015]

Full evaluation can be found at metric file of NER and metric file of entity span.

Training hyperparameters

The following hyperparameters were used during training:

• dataset: ['tner/bc5cdr']
• dataset_split: train
• dataset_name: None
• local_dataset: None
• model: microsoft/deberta-v3-large
• crf: True
• max_length: 128
• epoch: 15
• batch_size: 16
• lr: 1e-05
• random_seed: 42
• gradient_accumulation_steps: 4
• weight_decay: 1e-07
• lr_warmup_step_ratio: 0.1
• max_grad_norm: None

The full configuration can be found at fine-tuning parameter file.

Reference

If you use any resource from T-NER, please consider to cite our paper.

@inproceedings{ushio-camacho-collados-2021-ner,
    title = "{T}-{NER}: An All-Round Python Library for Transformer-based Named Entity Recognition",
    author = "Ushio, Asahi  and
      Camacho-Collados, Jose",
    booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations",
    month = apr,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.eacl-demos.7",
    doi = "10.18653/v1/2021.eacl-demos.7",
    pages = "53--62",
    abstract = "Language model (LM) pretraining has led to consistent improvements in many NLP downstream tasks, including named entity recognition (NER). In this paper, we present T-NER (Transformer-based Named Entity Recognition), a Python library for NER LM finetuning. In addition to its practical utility, T-NER facilitates the study and investigation of the cross-domain and cross-lingual generalization ability of LMs finetuned on NER. Our library also provides a web app where users can get model predictions interactively for arbitrary text, which facilitates qualitative model evaluation for non-expert programmers. We show the potential of the library by compiling nine public NER datasets into a unified format and evaluating the cross-domain and cross- lingual performance across the datasets. The results from our initial experiments show that in-domain performance is generally competitive across datasets. However, cross-domain generalization is challenging even with a large pretrained LM, which has nevertheless capacity to learn domain-specific features if fine- tuned on a combined dataset. To facilitate future research, we also release all our LM checkpoints via the Hugging Face model hub.",
}