emiltj's picture
update dacy pipeline
439d31d
{
"lang":"da",
"name":"dacy_medium_ner_fine_grained",
"version":"0.1.0",
"description":"\n<a href=\"https://github.com/centre-for-humanities-computing/Dacy\"><img src=\"https://centre-for-humanities-computing.github.io/DaCy/_static/icon.png\" width=\"175\" height=\"175\" align=\"right\" /></a>\n\n# DaCy_medium_ner_fine_grained\n\nDaCy is a Danish language processing framework with state-of-the-art pipelines as well as functionality for analyzing Danish pipelines.\nAt the time of publishing this model, also included in DaCy encorporates the only models for fine-grained NER using DANSK dataset - a dataset containing 18 annotation types in the same format as Ontonotes.\nMoreover, DaCy's largest pipeline has achieved State-of-the-Art performance on Named entity recognition, part-of-speech tagging and dependency parsing for Danish on the DaNE dataset. \nCheck out the [DaCy repository](https://github.com/centre-for-humanities-computing/DaCy) for material on how to use DaCy and reproduce the results. \nDaCy also contains guides on usage of the package as well as behavioural test for biases and robustness of Danish NLP pipelines.\n ",
"author":"Centre for Humanities Computing Aarhus",
"email":"Kenneth.enevoldsen@cas.au.dk",
"url":"https://chcaa.io/#/",
"license":"apache-2.0",
"spacy_version":">=3.5.0,<3.6.0",
"spacy_git_version":"Unknown",
"vectors":{
"width":0,
"vectors":0,
"keys":0,
"name":null
},
"labels":{
"transformer":[
],
"ner":[
"CARDINAL",
"DATE",
"EVENT",
"FACILITY",
"GPE",
"LANGUAGE",
"LAW",
"LOCATION",
"MONEY",
"NORP",
"ORDINAL",
"ORGANIZATION",
"PERCENT",
"PERSON",
"PRODUCT",
"QUANTITY",
"TIME",
"WORK OF ART"
]
},
"pipeline":[
"transformer",
"ner"
],
"components":[
"transformer",
"ner"
],
"disabled":[
],
"performance":{
"ents_f":0.8055281343,
"ents_p":0.7937743191,
"ents_r":0.8176352705,
"ents_per_type":{
"ORGANIZATION":{
"p":0.8376623377,
"r":0.8657718121,
"f":0.8514851485
},
"PERSON":{
"p":0.8875739645,
"r":0.8571428571,
"f":0.8720930233
},
"NORP":{
"p":0.8958333333,
"r":0.8775510204,
"f":0.8865979381
},
"CARDINAL":{
"p":0.7797356828,
"r":0.7831858407,
"f":0.7814569536
},
"GPE":{
"p":0.764957265,
"r":0.9274611399,
"f":0.8384074941
},
"DATE":{
"p":0.8248587571,
"r":0.8957055215,
"f":0.8588235294
},
"PRODUCT":{
"p":0.6184210526,
"r":0.6527777778,
"f":0.6351351351
},
"LOCATION":{
"p":0.7,
"r":0.7777777778,
"f":0.7368421053
},
"FACILITY":{
"p":0.5,
"r":0.5714285714,
"f":0.5333333333
},
"WORK OF ART":{
"p":0.6078431373,
"r":0.6739130435,
"f":0.6391752577
},
"TIME":{
"p":0.5,
"r":0.6666666667,
"f":0.5714285714
},
"MONEY":{
"p":1.0,
"r":1.0,
"f":1.0
},
"PERCENT":{
"p":0.9230769231,
"r":1.0,
"f":0.96
},
"QUANTITY":{
"p":0.5666666667,
"r":0.7727272727,
"f":0.6538461538
},
"ORDINAL":{
"p":0.7777777778,
"r":0.6363636364,
"f":0.7
},
"LANGUAGE":{
"p":1.0,
"r":0.3214285714,
"f":0.4864864865
},
"LAW":{
"p":0.7142857143,
"r":0.5555555556,
"f":0.625
},
"EVENT":{
"p":0.5555555556,
"r":0.5882352941,
"f":0.5714285714
}
},
"transformer_loss":172.7275591314,
"ner_loss":820.9019488291
},
"requirements":[
"spacy-transformers>=1.1.2,<1.2.0"
],
"datasets":"chcaa/DANSK",
"sources":[
{
"name":"DANSK - Danish Annotations for NLP Specific TasKs",
"url":"https://huggingface.co/datasets/chcaa/DANSK",
"license":"Creative Commons Attribution Share Alike 4.0 International",
"author":"chcaa"
},
{
"name":"vesteinn/DanskBERT",
"author":"V\u00e9steinn Sn\u00e6bjarnarson",
"url":"https://huggingface.co/vesteinn/DanskBERT",
"license":"agpl-3.0"
}
]
}