bert-base-NER / dslim_bert-base-NER.json
RiccardoDav's picture
add AIBOM
e58bdce verified
raw
history blame
8.33 kB
{
"bomFormat": "CycloneDX",
"specVersion": "1.6",
"serialNumber": "urn:uuid:2d71328a-f87c-48dc-9f4e-ba83929b1cb0",
"version": 1,
"metadata": {
"timestamp": "2025-06-05T09:39:43.530276+00:00",
"component": {
"type": "machine-learning-model",
"bom-ref": "dslim/bert-base-NER-40551b74-59a4-53a9-ae36-e1dca4f66e41",
"name": "dslim/bert-base-NER",
"externalReferences": [
{
"url": "https://huggingface.co/dslim/bert-base-NER",
"type": "documentation"
}
],
"modelCard": {
"modelParameters": {
"task": "token-classification",
"architectureFamily": "bert",
"modelArchitecture": "BertForTokenClassification",
"datasets": [
{
"ref": "conll2003-be67a053-25af-52ad-93c8-134501f8fa4b"
}
]
},
"properties": [
{
"name": "library_name",
"value": "transformers"
}
],
"quantitativeAnalysis": {
"performanceMetrics": [
{
"slice": "dataset: conll2003, split: test, config: conll2003",
"type": "accuracy",
"value": 0.9118041001560013
},
{
"slice": "dataset: conll2003, split: test, config: conll2003",
"type": "precision",
"value": 0.9211550382257732
},
{
"slice": "dataset: conll2003, split: test, config: conll2003",
"type": "recall",
"value": 0.9306415698281261
},
{
"slice": "dataset: conll2003, split: test, config: conll2003",
"type": "f1",
"value": 0.9258740048459675
},
{
"slice": "dataset: conll2003, split: test, config: conll2003",
"type": "loss",
"value": 0.48325642943382263
}
]
}
},
"authors": [
{
"name": "dslim"
}
],
"licenses": [
{
"license": {
"id": "MIT",
"url": "https://spdx.org/licenses/MIT.html"
}
}
],
"description": "**bert-base-NER** is a fine-tuned BERT model that is ready to use for **Named Entity Recognition** and achieves **state-of-the-art performance** for the NER task. It has been trained to recognize four types of entities: location (LOC), organizations (ORG), person (PER) and Miscellaneous (MISC).Specifically, this model is a *bert-base-cased* model that was fine-tuned on the English version of the standard [CoNLL-2003 Named Entity Recognition](https://www.aclweb.org/anthology/W03-0419.pdf) dataset.If you'd like to use a larger BERT-large model fine-tuned on the same dataset, a [**bert-large-NER**](https://huggingface.co/dslim/bert-large-NER/) version is also available.",
"tags": [
"transformers",
"pytorch",
"tf",
"jax",
"onnx",
"safetensors",
"bert",
"token-classification",
"en",
"dataset:conll2003",
"arxiv:1810.04805",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
}
},
"components": [
{
"type": "data",
"bom-ref": "conll2003-be67a053-25af-52ad-93c8-134501f8fa4b",
"name": "conll2003",
"data": [
{
"type": "dataset",
"bom-ref": "conll2003-be67a053-25af-52ad-93c8-134501f8fa4b",
"name": "conll2003",
"contents": {
"url": "https://huggingface.co/datasets/conll2003",
"properties": [
{
"name": "task_categories",
"value": "token-classification"
},
{
"name": "task_ids",
"value": "named-entity-recognition, part-of-speech"
},
{
"name": "language",
"value": "en"
},
{
"name": "size_categories",
"value": "10K<n<100K"
},
{
"name": "annotations_creators",
"value": "crowdsourced"
},
{
"name": "language_creators",
"value": "found"
},
{
"name": "pretty_name",
"value": "CoNLL-2003"
},
{
"name": "source_datasets",
"value": "extended|other-reuters-corpus"
},
{
"name": "paperswithcode_id",
"value": "conll-2003"
},
{
"name": "license",
"value": "other"
}
]
},
"governance": {
"owners": [
{
"organization": {
"name": "eriktks",
"url": "https://huggingface.co/eriktks"
}
}
]
},
"description": "The shared task of CoNLL-2003 concerns language-independent named entity recognition. We will concentrate on\nfour types of named entities: persons, locations, organizations and names of miscellaneous entities that do\nnot belong to the previous three groups.\n\nThe CoNLL-2003 shared task data files contain four columns separated by a single space. Each word has been put on\na separate line and there is an empty line after each sentence. The first item on each line is a word, the second\na part-of-speech (POS) tag, the third a syntactic chunk tag and the fourth the named entity tag. The chunk tags\nand the named entity tags have the format I-TYPE which means that the word is inside a phrase of type TYPE. Only\nif two phrases of the same type immediately follow each other, the first word of the second phrase will have tag\nB-TYPE to show that it starts a new phrase. A word with tag O is not part of a phrase. Note the dataset uses IOB2\ntagging scheme, whereas the original dataset uses IOB1.\n\nFor more details see https://www.clips.uantwerpen.be/conll2003/ner/ and https://www.aclweb.org/anthology/W03-0419"
}
]
}
]
}