Astral7/roberta-large-finetuned-ner

roberta-large-finetuned-ner

Model description

roberta-large-finetuned-ner is a fine-tuned Roberta model that is ready to use for Named Entity Recognition. It has been trained to recognize eight types of entities: Geographical, Organization, Person, Geopolitical Entity, Time indicator, Artifact, Event, Natural Phenomenon. This model is a fine-tuned version of FacebookAI/roberta-large on an Named Entity Recognition (NER) Corpus dataset.

It achieves the following results on the evaluation set:

• Train Loss: 0.1164
• Validation Loss: 0.0878
• Train Precision: 0.8442
• Train Recall: 0.8358
• Train F1: 0.8400
• Train Accuracy: 0.9718
• Epoch: 0

Intended uses & limitations

How to use:

You can use this model with Transformers pipeline for NER.

 from transformers import AutoTokenizer, TFAutoModelForTokenClassification
 from transformers import pipeline

 tokenizer = AutoTokenizer.from_pretrained("Astral7/roberta-large-finetuned-ner",add_prefix_space=True)
 model = TFAutoModelForTokenClassification.from_pretrained("Astral7/roberta-large-finetuned-ner")
 
 nlp_pipe = pipeline("token-classification", model=model,tokenizer=tokenizer )
 example = "My name is Clara and I live in Berkeley, California."

 results=nlp_pipe(example)
 print(results)

Limitations:

This model is limited by its training dataset of Annotated Corpus for Named Entity Recognition is annotated Corpus for Named Entity Recognition using GMB(Groningen Meaning Bank) corpus for entity classification with enhanced and popular features by Natural Language Processing applied to the data set.

Training and evaluation data

This model was fine-tuned on Corpus for Named Entity Recognition Dataset.

As in the dataset, each token will be classified as one of the following classes:

Abbreviation	Description
B-eve	Event
I-eve	Event
B-org	Organization
I-org	Organization
B-gpe	Geopolitical Entity
I-gpe	Geopolitical Entity
B-geo	Geographical
I-geo	Geographical
B-nat	Natural Phenomenon
I-nat	Natural Phenomenon
B-per	Person
I-per	Person
B-art	Art
I-art	Art
B-tim	Time
I-tim	Time

Training procedure

This model was trained on a single T4 GPU.

Training hyperparameters

The following hyperparameters were used during training:

• optimizer: { "name": "AdamWeightDecay", "learning_rate": { "module": "keras.optimizers.schedules", "class_name": "PolynomialDecay", "config": { "initial_learning_rate": 2e-05, "decay_steps": 4795, "end_learning_rate": 0.0, "power": 1.0, "cycle": False, "name": None, }, "registered_name": None, }, "decay": 0.0, "beta_1": 0.9, "beta_2": 0.999, "epsilon": 1e-08, "amsgrad": False, "weight_decay_rate": 0.01, } -
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Precision	Train Recall	Train F1	Train Accuracy	Epoch
0.1164	0.0878	0.8442	0.8358	0.8400	0.9718	0

Framework versions

• Transformers 4.35.2
• TensorFlow 2.15.0
• Datasets 2.17.1
• Tokenizers 0.15.2