README.md

metadata

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.

Intended uses & limitations

How to use

You can use this model with Transformers pipeline for NER.

from transformers import AutoTokenizer, AutoModelForTokenClassification
from transformers import pipeline

model_checkpoint = "pietruszkowiec/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)

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",
    abstract = "The ambitious goal of this work is to develop a cross-lingual name tagging and linking framework for 282 languages that exist in Wikipedia. Given a document in any of these languages, our framework is able to identify name mentions, assign a coarse-grained or fine-grained type to each mention, and link it to an English Knowledge Base (KB) if it is linkable. We achieve this goal by performing a series of new KB mining methods: generating {``}silver-standard{''} annotations by transferring annotations from English to other languages through cross-lingual links and KB properties, refining annotations through self-training and topic selection, deriving language-specific morphology features from anchor links, and mining word translation pairs from cross-lingual links. Both name tagging and linking results for 282 languages are promising on Wikipedia data and on-Wikipedia data.",
}