metadata

language:
  - tl
license: gpl-3.0
library_name: span-marker
tags:
  - span-marker
  - token-classification
  - ner
  - named-entity-recognition
  - generated_from_span_marker_trainer
datasets:
  - ljvmiranda921/tlunified-ner
metrics:
  - precision
  - recall
  - f1
widget:
  - text: >-
      MANILA - Binalewala ng Philippine National Police (PNP) nitong Sabado ang
      posibleng paglulunsad ng tinatawag na " sympathy attacks " ng Moro
      National Liberation Front (MNLF) at Abu Sayyaf matapos arestuhin si
      Indanan, Sulu Mayor Alvarez Isnaji.
  - text: >-
      Pinatawan din ng apat na buwang suspensyon si Herma Gonzales - Escudero,
      chief revenue officer III ng BIR - Cotabato City, dahil sa kasong
      dishonesty at limang kaso ng perjury sa Municipal Trial Court ng Cotabato
      City . Bunga ito ng kanyang kabiguan na ideklara sa kanyang SALN noong
      2002 - 2004 ang 200 metro kwadradong lote sa South Cotabato at Toyota Revo
      noong 2001 SALN at undervaluation ng kanyang mga ari - arian sa lalawigan
      noong 2000 - 2004 SALN.
  - text: >-
      Sa tila pagpapabaya sa mga magsasaka, sinabi ni Escudero na hindi
      mangyayari ang pangarap ng Department of Agriculture (DA) na maging self -
      sufficient ang Pilipinas sa bigas.
  - text: >-
      MANILA - Tiniyak ng pinuno ng Government Service Insurance System (GSIS)
      na tatapatan nito ang pro - Meralco advertisement ni Judy Ann Santos upang
      isulong ang kanyang posisyon na dapat ibaba ang singil sa kuryente.
  - text: >-
      Idinagdag ni South Cotabato Rep Darlene Antonino - Custodio, na illegal na
      ipagpaliban ang halalan sa ARMM kung ang gagamitin lamang basehan ay ang
      ipapasang panukala ng Kongreso.
pipeline_tag: token-classification
co2_eq_emissions:
  emissions: 22.090476722294312
  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: 0.238
  hardware_used: 1 x NVIDIA GeForce RTX 3090
base_model: bert-base-multilingual-cased
model-index:
  - name: SpanMarker with bert-base-multilingual-cased on TLUnified
    results:
      - task:
          type: token-classification
          name: Named Entity Recognition
        dataset:
          name: TLUnified
          type: ljvmiranda921/tlunified-ner
          split: test
        metrics:
          - type: f1
            value: 0.8886810102899907
            name: F1
          - type: precision
            value: 0.8736971183323115
            name: Precision
          - type: recall
            value: 0.9041878172588832
            name: Recall

SpanMarker with bert-base-multilingual-cased on TLUnified

This is a SpanMarker model trained on the TLUnified dataset that can be used for Named Entity Recognition. This SpanMarker model uses bert-base-multilingual-cased as the underlying encoder.

Model Details

Model Description

Model Type: SpanMarker
Encoder: bert-base-multilingual-cased
Maximum Sequence Length: 256 tokens
Maximum Entity Length: 8 words
Training Dataset: TLUnified
Language: tl
License: gpl-3.0

Model Sources

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

Model Labels

Label	Examples
LOC	"Israel", "Batasan", "United States"
ORG	"MMDA", "International Monitoring Team", "Coordinating Committees for the Cessation of Hostilities"
PER	"Puno", "Fernando", "Villavicencio"

Evaluation

Metrics

Label	Precision	Recall	F1
all	0.8737	0.9042	0.8887
LOC	0.8830	0.9084	0.8955
ORG	0.7579	0.8587	0.8052
PER	0.9264	0.9220	0.9242

Uses

Direct Use for Inference

from span_marker import SpanMarkerModel

# Download from the 🤗 Hub
model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-mbert-base-tlunified")
# Run inference
entities = model.predict("Idinagdag ni South Cotabato Rep Darlene Antonino - Custodio, na illegal na ipagpaliban ang halalan sa ARMM kung ang gagamitin lamang basehan ay ang ipapasang panukala ng Kongreso.")

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-mbert-base-tlunified")

# 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-mbert-base-tlunified-finetuned")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Sentence length	1	31.7625	150
Entities per sentence	0	2.0661	38

Training Hyperparameters

learning_rate: 5e-05
train_batch_size: 16
eval_batch_size: 16
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
0.6803	400	0.0074	0.8552	0.8835	0.8691	0.9774
1.3605	800	0.0072	0.8709	0.9034	0.8869	0.9798
2.0408	1200	0.0070	0.8753	0.9053	0.8900	0.9812
2.7211	1600	0.0065	0.8876	0.9003	0.8939	0.9807

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Carbon Emitted: 0.022 kg of CO2
Hours Used: 0.238 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}
}