metadata

library_name: span-marker
tags:
  - span-marker
  - token-classification
  - ner
  - named-entity-recognition
  - generated_from_span_marker_trainer
datasets:
  - conll2003
metrics:
  - precision
  - recall
  - f1
widget:
  - text: >-
      New Zealand Prime Minister Jim Bolger, emerging from coalition talks with
      the nationalist New Zealand First party on Friday afternoon, said National
      and NZ First would meet again on Sunday.
  - text: >-
      A police spokesman said two youths believed to be supporters of President
      Nelson Mandela's African National Congress (ANC) had been killed when
      unknown gunmen opened fire at the rural settlement of Izingolweni on
      KwaZulu-Natal province's south coast on Thursday night.
  - text: >-
      Japan's Economic Planning Agency has not changed its view that the economy
      is gradually recovering, despite relatively weak gross domestic product
      figures released on Tuesday, EPA Vice Minister Shimpei Nukaya told
      reporters on Friday.
  - text: >-
      Cuttitta, who trainer George Coste said was certain to play on Saturday
      week, was named in a 21-man squad lacking only two of the team beaten
      54-21 by England at Twickenham last month.
  - text: Dong Jiong (China) beat Thomas Stuer-Lauridsen (Denmark) 15-10 15-6
pipeline_tag: token-classification
model-index:
  - name: SpanMarker
    results:
      - task:
          type: token-classification
          name: Named Entity Recognition
        dataset:
          name: Unknown
          type: conll2003
          split: test
        metrics:
          - type: f1
            value: 0.9209646189051223
            name: F1
          - type: precision
            value: 0.9156457822891144
            name: Precision
          - type: recall
            value: 0.9263456090651558
            name: Recall

SpanMarker

This is a SpanMarker model trained on the conll2003 dataset that can be used for Named Entity Recognition.

Model Details

Model Description

Model Type: SpanMarker
Maximum Sequence Length: 256 tokens
Maximum Entity Length: 8 words
Training Dataset: conll2003

Model Sources

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

Model Labels

Label	Examples
LOC	"BRUSSELS", "Britain", "Germany"
MISC	"British", "EU-wide", "German"
ORG	"European Union", "EU", "European Commission"
PER	"Nikolaus van der Pas", "Peter Blackburn", "Werner Zwingmann"

Evaluation

Metrics

Label	Precision	Recall	F1
all	0.9156	0.9263	0.9210
LOC	0.9327	0.9394	0.9361
MISC	0.7973	0.8462	0.8210
ORG	0.8987	0.9133	0.9059
PER	0.9706	0.9610	0.9658

Uses

Direct Use for Inference

from span_marker import SpanMarkerModel

# Download from the 🤗 Hub
model = SpanMarkerModel.from_pretrained("supreethrao/instructNER_conll03_xl")
# Run inference
entities = model.predict("Dong Jiong (China) beat Thomas Stuer-Lauridsen (Denmark) 15-10 15-6")

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("supreethrao/instructNER_conll03_xl")

# 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("supreethrao/instructNER_conll03_xl-finetuned")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Sentence length	1	14.5019	113
Entities per sentence	0	1.6736	20

Training Hyperparameters

learning_rate: 5e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
num_devices: 2
total_train_batch_size: 32
total_eval_batch_size: 32
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
mixed_precision_training: Native AMP

Framework Versions

Python: 3.10.13
SpanMarker: 1.5.0
Transformers: 4.35.2
PyTorch: 2.1.1
Datasets: 2.15.0
Tokenizers: 0.15.0

Citation

BibTeX

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