Nbailab Base Ner Scandi

🚀 ScandiNER - Named Entity Recognition model for Scandinavian Languages

This model is a fine - tuned version of [NbAiLab/nb - bert - base](https://huggingface.co/NbAiLab/nb - bert - base) designed for Named Entity Recognition in Danish, Norwegian (both Bokmål and Nynorsk), Swedish, Icelandic, and Faroese. It can also handle English sentences reasonably well as the pretrained model was trained on English data alongside Scandinavian languages. Check out a demo of the model [here](https://huggingface.co/spaces/alexandrainst/named - entity - recognition).

🚀 Quick Start

You can use this model in your scripts as follows:

Basic Usage

>>> from transformers import pipeline
>>> import pandas as pd
>>> ner = pipeline(task='ner', 
...                model='saattrupdan/nbailab - base - ner - scandi', 
...                aggregation_strategy='first')
>>> result = ner('Borghild kjøper seg inn i Bunnpris')
>>> pd.DataFrame.from_records(result)
  entity_group     score      word  start  end
0          PER  0.981257  Borghild      0    8
1          ORG  0.974099  Bunnpris     26   34

✨ Features

• Multilingual Support: Covers multiple Scandinavian languages including Danish, Norwegian (Bokmål and Nynorsk), Swedish, Icelandic, and Faroese.
• Good English Compatibility: Works reasonably well on English sentences.
• High Accuracy: Demonstrates high Micro - F1 NER performance on Scandinavian NER test datasets.
• Efficiency: Substantially smaller and faster than the previous state - of - the - art models.

📦 Installation

No specific installation steps are provided in the original document.

📚 Documentation

Entities Predicted

The model will predict the following four entities:

Performance

The following is the Micro - F1 NER performance on Scandinavian NER test datasets, compared with the current state - of - the - art. The models have been evaluated on the test set along with 9 bootstrapped versions of it, with the mean and 95% confidence interval shown here:

Aside from its high accuracy, it's also substantially smaller and faster than the previous state - of - the - art:

Training Procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e - 05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 90135.90000000001
• num_epochs: 1000

Training results

Framework versions

• Transformers 4.10.3
• Pytorch 1.9.0+cu102
• Datasets 1.12.1
• Tokenizers 0.10.3

🔧 Technical Details

The model is fine - tuned on the concatenation of [DaNE](https://aclanthology.org/2020.lrec - 1.565/), NorNE, SUC 3.0 and the Icelandic and Faroese parts of the [WikiANN](https://aclanthology.org/P17 - 1178/) dataset.

📄 License

This project is licensed under the MIT license.

Information Table