metadata

language:
  - en
license: cc-by-sa-4.0
library_name: span-marker
tags:
  - span-marker
  - token-classification
  - ner
  - named-entity-recognition
  - generated_from_span_marker_trainer
datasets:
  - tomaarsen/ner-orgs
metrics:
  - precision
  - recall
  - f1
widget:
  - text: >-
      In 2005, Shankel signed with Warner Chappell Music and while pursuing his
      own projects created another joint venture, Shankel Songs and signed Ben
      Glover, "Billboard "'s Christian writer of the Year, 2010, Joy Williams of
      The Civil Wars, and, whom he also produced.
  - text: >-
      In 2002, Rodríguez moved to Mississippi and to the NASA Stennis Space
      Center as the Director of Center Operations and as a member of the Senior
      Executive Service where he managed facility construction, security and
      other programs for 4,500 Stennis personnel.
  - text: >-
      American Motors included Chinese officials as part of the negotiations
      establishing Beijing Jeep (now Beijing Benz).
  - text: >-
      La Señora () is a popular Spanish television period drama series set in
      the 1920s, produced by Diagonal TV for Televisión Española that was
      broadcast on La 1 of Televisión Española from 2008 to 2010.
  - text: >-
      Not only did the Hungarian Ministry of Foreign Affairs approve Radio Free
      Europe's new location, but the Ministry of Telecommunications did
      something even more amazing: "They found us four phone lines in central
      Budapest," says Geza Szocs, a Radio Free Europe correspondent who helped
      organize the Budapest location.
pipeline_tag: token-classification
co2_eq_emissions:
  emissions: 67.93561835707102
  source: codecarbon
  training_type: fine-tuning
  on_cloud: false
  cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
  ram_total_size: 31.777088165283203
  hours_used: 0.52
  hardware_used: 1 x NVIDIA GeForce RTX 3090
base_model: prajjwal1/bert-small
model-index:
  - name: >-
      SpanMarker with prajjwal1/bert-small on FewNERD, CoNLL2003, and OntoNotes
      v5
    results:
      - task:
          type: token-classification
          name: Named Entity Recognition
        dataset:
          name: FewNERD, CoNLL2003, and OntoNotes v5
          type: tomaarsen/ner-orgs
          split: test
        metrics:
          - type: f1
            value: 0.7547025470254703
            name: F1
          - type: precision
            value: 0.7617641715116279
            name: Precision
          - type: recall
            value: 0.7477706438380596
            name: Recall

SpanMarker with prajjwal1/bert-small on FewNERD, CoNLL2003, and OntoNotes v5

This is a SpanMarker model trained on the FewNERD, CoNLL2003, and OntoNotes v5 dataset that can be used for Named Entity Recognition. This SpanMarker model uses prajjwal1/bert-small as the underlying encoder.

Model Details

Model Description

Model Type: SpanMarker
Encoder: prajjwal1/bert-small
Maximum Sequence Length: 256 tokens
Maximum Entity Length: 8 words
Training Dataset: FewNERD, CoNLL2003, and OntoNotes v5
Language: en
License: cc-by-sa-4.0

Model Sources

Repository: SpanMarker on GitHub
Thesis: SpanMarker For Named Entity Recognition

Model Labels

Label	Examples
ORG	"Texas Chicken", "Church 's Chicken", "IAEA"

Evaluation

Metrics

Label	Precision	Recall	F1
all	0.7618	0.7478	0.7547
ORG	0.7618	0.7478	0.7547

Uses

Direct Use for Inference

from span_marker import SpanMarkerModel

# Download from the 🤗 Hub
model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-bert-small-orgs")
# Run inference
entities = model.predict("American Motors included Chinese officials as part of the negotiations establishing Beijing Jeep (now Beijing Benz).")

Downstream Use

You can finetune this model on your own dataset.

Click to expand

from span_marker import SpanMarkerModel, Trainer

# Download from the 🤗 Hub
model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-bert-small-orgs")

# Specify a Dataset with "tokens" and "ner_tag" columns
dataset = load_dataset("conll2003") # For example CoNLL2003

# Initialize a Trainer using the pretrained model & dataset
trainer = Trainer(
    model=model,
    train_dataset=dataset["train"],
    eval_dataset=dataset["validation"],
)
trainer.train()
trainer.save_model("tomaarsen/span-marker-bert-small-orgs-finetuned")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Sentence length	1	23.5706	263
Entities per sentence	0	0.7865	39

Training Hyperparameters

learning_rate: 0.0001
train_batch_size: 128
eval_batch_size: 128
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3

Training Results

Epoch	Step	Validation Loss	Validation Precision	Validation Recall	Validation F1	Validation Accuracy
0.5720	600	0.0076	0.7642	0.6630	0.7100	0.9656
1.1439	1200	0.0070	0.7705	0.7139	0.7411	0.9699
1.7159	1800	0.0067	0.7837	0.7231	0.7522	0.9709
2.2879	2400	0.0070	0.7768	0.7517	0.7640	0.9725
2.8599	3000	0.0068	0.7877	0.7374	0.7617	0.9718

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Carbon Emitted: 0.068 kg of CO2
Hours Used: 0.52 hours

Training Hardware

On Cloud: No
GPU Model: 1 x NVIDIA GeForce RTX 3090
CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
RAM Size: 31.78 GB

Framework Versions

Python: 3.9.16
SpanMarker: 1.5.1.dev
Transformers: 4.30.0
PyTorch: 2.0.1+cu118
Datasets: 2.14.0
Tokenizers: 0.13.3

Citation

BibTeX

@software{Aarsen_SpanMarker,
    author = {Aarsen, Tom},
    license = {Apache-2.0},
    title = {{SpanMarker for Named Entity Recognition}},
    url = {https://github.com/tomaarsen/SpanMarkerNER}
}