This is a SpanMarker model trained on the FewNERD dataset that can be used for Named Entity Recognition. This SpanMarker model uses roberta-large as the underlying encoder. See train.py for the training script.

Model Details

Model Description

Model Type: SpanMarker
Encoder: roberta-large
Maximum Sequence Length: 256 tokens
Maximum Entity Length: 8 words
Training Dataset: FewNERD
Language: en
License: cc-by-sa-4.0

Model Sources

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

Model Labels

Label	Examples
art-broadcastprogram	"Street Cents", "The Gale Storm Show : Oh , Susanna", "Corazones"
art-film	"Shawshank Redemption", "Bosch", "L'Atlantide"
art-music	"Hollywood Studio Symphony", "Champion Lover", "Atkinson , Danko and Ford ( with Brockie and Hilton )"
art-other	"Aphrodite of Milos", "Venus de Milo", "The Today Show"
art-painting	"Production/Reproduction", "Cofiwch Dryweryn", "Touit"
art-writtenart	"Imelda de ' Lambertazzi", "Time", "The Seven Year Itch"
building-airport	"Sheremetyevo International Airport", "Newark Liberty International Airport", "Luton Airport"
building-hospital	"Memorial Sloan-Kettering Cancer Center", "Hokkaido University Hospital", "Yeungnam University Hospital"
building-hotel	"Flamingo Hotel", "The Standard Hotel", "Radisson Blu Sea Plaza Hotel"
building-library	"British Library", "Berlin State Library", "Bayerische Staatsbibliothek"
building-other	"Alpha Recording Studios", "Henry Ford Museum", "Communiplex"
building-restaurant	"Fatburger", "Carnegie Deli", "Trumbull"
building-sportsfacility	"Sports Center", "Glenn Warner Soccer Facility", "Boston Garden"
building-theater	"Pittsburgh Civic Light Opera", "National Paris Opera", "Sanders Theatre"
event-attack/battle/war/militaryconflict	"Jurist", "Vietnam War", "Easter Offensive"
event-disaster	"the 1912 North Mount Lyell Disaster", "1990s North Korean famine", "1693 Sicily earthquake"
event-election	"March 1898 elections", "Elections to the European Parliament", "1982 Mitcham and Morden by-election"
event-other	"Eastwood Scoring Stage", "Union for a Popular Movement", "Masaryk Democratic Movement"
event-protest	"Russian Revolution", "French Revolution", "Iranian Constitutional Revolution"
event-sportsevent	"World Cup", "Stanley Cup", "National Champions"
location-GPE	"Croatian", "the Republic of Croatia", "Mediterranean Basin"
location-bodiesofwater	"Arthur Kill", "Norfolk coast", "Atatürk Dam Lake"
location-island	"new Samsat district", "Staten Island", "Laccadives"
location-mountain	"Ruweisat Ridge", "Salamander Glacier", "Miteirya Ridge"
location-other	"Northern City Line", "Victoria line", "Cartuther"
location-park	"Gramercy Park", "Shenandoah National Park", "Painted Desert Community Complex Historic District"
location-road/railway/highway/transit	"NJT", "Friern Barnet Road", "Newark-Elizabeth Rail Link"
organization-company	"Church 's Chicken", "Dixy Chicken", "Texas Chicken"
organization-education	"MIT", "Barnard College", "Belfast Royal Academy and the Ulster College of Physical Education"
organization-government/governmentagency	"Supreme Court", "Congregazione dei Nobili", "Diet"
organization-media/newspaper	"Al Jazeera", "Clash", "TimeOut Melbourne"
organization-other	"IAEA", "4th Army", "Defence Sector C"
organization-politicalparty	"Al Wafa ' Islamic", "Kenseitō", "Shimpotō"
organization-religion	"Jewish", "UPCUSA", "Christian"
organization-showorganization	"Mr. Mister", "Lizzy", "Bochumer Symphoniker"
organization-sportsleague	"China League One", "NHL", "First Division"
organization-sportsteam	"Arsenal", "Luc Alphand Aventures", "Tottenham"
other-astronomything	"Algol", "`` Caput Larvae ''", "Zodiac"
other-award	"GCON", "Grand Commander of the Order of the Niger", "Order of the Republic of Guinea and Nigeria"
other-biologything	"BAR", "N-terminal lipid", "Amphiphysin"
other-chemicalthing	"carbon dioxide", "sulfur", "uranium"
other-currency	"$", "Travancore Rupee", "lac crore"
other-disease	"bladder cancer", "French Dysentery Epidemic of 1779", "hypothyroidism"
other-educationaldegree	"Bachelor", "Master", "BSc ( Hons ) in physics"
other-god	"El", "Fujin", "Raijin"
other-language	"Latin", "Breton-speaking", "English"
other-law	"Leahy–Smith America Invents Act ( AIA", "Thirty Years ' Peace", "United States Freedom Support Act"
other-livingthing	"monkeys", "patchouli", "insects"
other-medical	"Pediatrics", "pediatrician", "amitriptyline"
person-actor	"Tchéky Karyo", "Ellaline Terriss", "Edmund Payne"
person-artist/author	"George Axelrod", "Gaetano Donizett", "Hicks"
person-athlete	"Jaguar", "Tozawa", "Neville"
person-director	"Bob Swaim", "Frank Darabont", "Richard Quine"
person-other	"Richard Benson", "Holden", "Campbell"
person-politician	"Emeric", "Rivière", "William"
person-scholar	"Stalmine", "Stedman", "Wurdack"
person-soldier	"Helmuth Weidling", "Joachim Ziegler", "Krukenberg"
product-airplane	"Luton", "Spey-equipped FGR.2s", "EC135T2 CPDS"
product-car	"100EX", "Phantom", "Corvettes - GT1 C6R"
product-food	"red grape", "yakiniku", "V. labrusca"
product-game	"Airforce Delta", "Splinter Cell", "Hardcore RPG"
product-other	"Fairbottom Bobs", "X11", "PDP-1"
product-ship	"HMS `` Chinkara ''", "Congress", "Essex"
product-software	"Wikipedia", "Apdf", "AmiPDF"
product-train	"Royal Scots Grey", "High Speed Trains", "55022"
product-weapon	"AR-15 's", "ZU-23-2M Wróbel", "ZU-23-2MR Wróbel II"

Uses

Direct Use

python

from span_marker import SpanMarkerModel

# Download from the 🤗 Hub
model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-roberta-large-fewnerd-fine-super")
# Run inference
entities = model.predict("Most of the Steven Seagal movie ``Under Siege`` (co-starring Tommy Lee Jones) was filmed aboard the Battleship USS Alabama, which is docked on Mobile Bay at Battleship Memorial Park and open to the public.")

Downstream Use

You can finetune this model on your own dataset.

Click to expand

python

from span_marker import SpanMarkerModel, Trainer

# Download from the 🤗 Hub
model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-roberta-large-fewnerd-fine-super")

# 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-roberta-large-fewnerd-fine-super-finetuned")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Sentence length	1	24.4945	267
Entities per sentence	0	2.5832	88

Training Hyperparameters

learning_rate: 1e-05
train_batch_size: 8
eval_batch_size: 8
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 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 : 4.29.2
PyTorch: 2.0.1+cu118
Datasets: 2.14.3
Tokenizers: 0.13.2