metadata
language:
- et
base_model:
- EMBEDDIA/est-roberta
pipeline_tag: token-classification
library_name: transformers
tags:
- NER
license: cc-by-4.0
est-roberta-ud-ner
Model Description
est-roberta-ud-ner is an Est-RoBERTa based model fine-tuned for named entity recognition in Estonian on the EDT and EWT datasets.
How to use
The model can be used with Transformers pipeline for NER. Try it in Google Colab, where the Transformers library is pre-installed or on your local machine (preferably using a virtual environment, see tutorial below) and install the Transformers library using pip install transformers.
from transformers import pipeline
ner = pipeline("ner", model="vbius01/est-roberta-ud-ner")
text = "Eesti kuulub erinevalt Lätist ja Leedust kahtlemata Põhjamaade kultuuriruumi."
results = ner(text)
print(results)
[{'entity': 'B-GEP', 'score': np.float32(0.99339926), 'index': 1, 'word': '▁Eesti', 'start': 0, 'end': 5}, {'entity': 'B-GEP', 'score': np.float32(0.9923631), 'index': 4, 'word': '▁Lätist', 'start': 22, 'end': 29}, {'entity': 'B-GEP', 'score': np.float32(0.990756), 'index': 6, 'word': '▁Leedust', 'start': 32, 'end': 40}, {'entity': 'B-LOC', 'score': np.float32(0.61792), 'index': 8, 'word': '▁Põhjamaade', 'start': 51, 'end': 62}]
- Repository: github.com/martinkivisikk/ner_thesis
- Paper: Developing a NER Model Based on Treebank Corpora
Virtual environment setup
Create and activate a virtual environment in your project directory with venv.
python -m venv .env
source .env/bin/activate
Uses
This model can be used to find named entities from Estonian texts.