est-roberta-ud-ner

est-roberta-ud-ner

<!-- Provide a quick summary of what the model is/does. -->

Model Description

<!-- Provide a longer summary of what this model is. -->

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}]

<!-- Provide the basic links for the model. -->

• 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

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

This model can be used to find named entities from Estonian texts.