metadata

language:
  - en
license: apache-2.0
library_name: span-marker
tags:
  - span-marker
  - token-classification
  - ner
  - named-entity-recognition
  - generated_from_span_marker_trainer
datasets:
  - acronym_identification
metrics:
  - precision
  - recall
  - f1
widget:
  - text: >-
      here, da = direct assessment, rr = relative ranking, ds = discrete scale
      and cs = continuous scale.
    example_title: Uncased 1
  - text: >-
      modifying or replacing the erasable programmable read only memory (eprom)
      in a phone would allow the configuration of any esn and min via software
      for cellular devices.
    example_title: Uncased 2
  - text: >-
      we propose a technique called aggressive stochastic weight averaging
      (aswa) and an extension called norm-filtered aggressive stochastic weight
      averaging (naswa) which improves te stability of models over random seeds.
    example_title: Uncased 3
  - text: >-
      the choice of the encoder and decoder modules of dnpg can be quite
      flexible, for instance long-short term memory networks (lstm) or
      convolutional neural network (cnn).
    example_title: Uncased 4
pipeline_tag: token-classification
co2_eq_emissions:
  emissions: 31.203903222402037
  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: 0.272
  hardware_used: 1 x NVIDIA GeForce RTX 3090
base_model: bert-base-uncased
model-index:
  - name: SpanMarker with bert-base-uncased on Acronym Identification
    results:
      - task:
          type: token-classification
          name: Named Entity Recognition
        dataset:
          name: Acronym Identification
          type: acronym_identification
          split: validation
        metrics:
          - type: f1
            value: 0.9198933333333332
            name: F1
          - type: precision
            value: 0.9339397877409573
            name: Precision
          - type: recall
            value: 0.9062631357713324
            name: Recall

SpanMarker with bert-base-uncased on Acronym Identification

This is a SpanMarker model trained on the Acronym Identification dataset that can be used for Named Entity Recognition. This SpanMarker model uses bert-base-uncased as the underlying encoder. See train.py for the training script.

Is your data always capitalized correctly? Then consider using the cased variant of this model instead for better performance: tomaarsen/span-marker-bert-base-acronyms.

Model Details

Model Description

Model Type: SpanMarker
Encoder: bert-base-uncased
Maximum Sequence Length: 256 tokens
Maximum Entity Length: 8 words
Training Dataset: Acronym Identification
Language: en
License: apache-2.0

Model Sources

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

Model Labels

Label	Examples
long	"successive convex approximation", "controlled natural language", "Conversational Question Answering"
short	"SODA", "CNL", "CoQA"

Evaluation

Metrics

Label	Precision	Recall	F1
all	0.9339	0.9063	0.9199
long	0.9314	0.8845	0.9074
short	0.9352	0.9174	0.9262

Uses

Direct Use for Inference

from span_marker import SpanMarkerModel

# Download from the 🤗 Hub
model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-bert-base-uncased-acronyms")
# Run inference
entities = model.predict("compression algorithms like principal component analysis (pca) can reduce noise and complexity.")

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-base-uncased-acronyms")

# 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-base-uncased-acronyms-finetuned")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Sentence length	4	32.3372	170
Entities per sentence	0	2.6775	24

Training Hyperparameters

learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 32
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: 2

Training Results

Epoch	Step	Validation Loss	Validation Precision	Validation Recall	Validation F1	Validation Accuracy
0.3120	200	0.0097	0.8999	0.8731	0.8863	0.9718
0.6240	400	0.0075	0.9163	0.8995	0.9078	0.9769
0.9360	600	0.0076	0.9079	0.9153	0.9116	0.9773
1.2480	800	0.0069	0.9267	0.9006	0.9135	0.9778
1.5601	1000	0.0065	0.9268	0.9044	0.9154	0.9782
1.8721	1200	0.0065	0.9279	0.9061	0.9168	0.9787

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Carbon Emitted: 0.031 kg of CO2
Hours Used: 0.272 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: 1.3.1.dev
Transformers: 4.30.0
PyTorch: 2.0.1+cu118
Datasets: 2.14.0
Tokenizers: 0.13.2

Citation

BibTeX

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