license: cc-by-4.0 datasets:

• wikiann language:
• pl pipeline_tag: token-classification widget:
• text: "Nazywam się Grzegorz Brzęszczyszczykiewicz, pochodzę z Chrząszczyżewoszczyc, pracuję w Łękołodzkim Urzędzie Powiatowym"
• text: "Jestem Krzysiek i pracuję w Ministerstwie Sportu"
• text: "Na imię jej Wiktoria, pracuje w Krakowie na AGH" model-index:
• name: herbert-base-ner results:
  • task: name: Token Classification type: token-classification dataset: name: wikiann type: wikiann config: pl split: test args: pl metrics:
    • name: Precision type: precision value: 0.8857142857142857
    • name: Recall type: recall value: 0.9070532179048386
    • name: F1 type: f1 value: 0.896256755412619
    • name: Accuracy type: accuracy value: 0.9581463871961428

herbert-base-ner

Model description

herbert-base-ner is a fine-tuned HerBERT model that can be used for Named Entity Recognition . It has been trained to recognize three types of entities: person (PER), location (LOC) and organization (ORG).

Specifically, this model is an allegro/herbert-base-cased model that was fine-tuned on the Polish subset of wikiann dataset.

How to use

You can use this model with Transformers pipeline for NER.

from transformers import AutoTokenizer, AutoModelForTokenClassification
from transformers import pipeline

model_checkpoint = "pczarnik/herbert-base-ner"
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
model = AutoModelForTokenClassification.from_pretrained(model_checkpoint)

nlp = pipeline("ner", model=model, tokenizer=tokenizer)
example = "Nazywam się Grzegorz Brzęszczyszczykiewicz, pochodzę "\
    "z Chrząszczyżewoszczyc, pracuję w Łękołodzkim Urzędzie Powiatowym"

ner_results = nlp(example)
print(ner_results)

[{'entity': 'B-PER', 'score': 0.99451494, 'index': 4, 'word': 'Grzegorz</w>', 'start': 12, 'end': 20},
 {'entity': 'I-PER', 'score': 0.99758506, 'index': 5, 'word': 'B', 'start': 21, 'end': 22},
 {'entity': 'I-PER', 'score': 0.99749386, 'index': 6, 'word': 'rzę', 'start': 22, 'end': 25},
 {'entity': 'I-PER', 'score': 0.9973041, 'index': 7, 'word': 'szczy', 'start': 25, 'end': 30},
 {'entity': 'I-PER', 'score': 0.99682057, 'index': 8, 'word': 'szczy', 'start': 30, 'end': 35},
 {'entity': 'I-PER', 'score': 0.9964832, 'index': 9, 'word': 'kiewicz</w>', 'start': 35, 'end': 42},
 {'entity': 'B-LOC', 'score': 0.99427444, 'index': 14, 'word': 'Chrzą', 'start': 55, 'end': 60},
 {'entity': 'I-LOC', 'score': 0.99143463, 'index': 15, 'word': 'szczy', 'start': 60, 'end': 65},
 {'entity': 'I-LOC', 'score': 0.9922201, 'index': 16, 'word': 'że', 'start': 65, 'end': 67},
 {'entity': 'I-LOC', 'score': 0.9918464, 'index': 17, 'word': 'wo', 'start': 67, 'end': 69},
 {'entity': 'I-LOC', 'score': 0.9900766, 'index': 18, 'word': 'szczy', 'start': 69, 'end': 74},
 {'entity': 'I-LOC', 'score': 0.98823845, 'index': 19, 'word': 'c</w>', 'start': 74, 'end': 75},
 {'entity': 'B-ORG', 'score': 0.6808262, 'index': 23, 'word': 'Łę', 'start': 87, 'end': 89},
 {'entity': 'I-ORG', 'score': 0.7763973, 'index': 24, 'word': 'ko', 'start': 89, 'end': 91},
 {'entity': 'I-ORG', 'score': 0.77731717, 'index': 25, 'word': 'ło', 'start': 91, 'end': 93},
 {'entity': 'I-ORG', 'score': 0.9108255, 'index': 26, 'word': 'dzkim</w>', 'start': 93, 'end': 98},
 {'entity': 'I-ORG', 'score': 0.98050755, 'index': 27, 'word': 'Urzędzie</w>', 'start': 99, 'end': 107},
 {'entity': 'I-ORG', 'score': 0.9789752, 'index': 28, 'word': 'Powiatowym</w>', 'start': 108, 'end': 118}]

BibTeX entry and citation info

@inproceedings{mroczkowski-etal-2021-herbert,
    title = "{H}er{BERT}: Efficiently Pretrained Transformer-based Language Model for {P}olish",
    author = "Mroczkowski, Robert  and
      Rybak, Piotr  and
      Wr{\\'o}blewska, Alina  and
      Gawlik, Ireneusz",
    booktitle = "Proceedings of the 8th Workshop on Balto-Slavic Natural Language Processing",
    month = apr,
    year = "2021",
    address = "Kiyv, Ukraine",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2021.bsnlp-1.1",
    pages = "1--10",
}

@inproceedings{pan-etal-2017-cross,
    title = "Cross-lingual Name Tagging and Linking for 282 Languages",
    author = "Pan, Xiaoman  and
      Zhang, Boliang  and
      May, Jonathan  and
      Nothman, Joel  and
      Knight, Kevin  and
      Ji, Heng",
    booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2017",
    address = "Vancouver, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/P17-1178",
    doi = "10.18653/v1/P17-1178",
    pages = "1946--1958",
}