skatturinn/isat-2008

Classifying Text into NACE Codes

This model is xlm-roberta-base fine-tuned to classify descriptions of activities into NACE Rev. 2 codes. It is based on xlm-roberta-base-finetuned-nace.

Data

The data used to fine-tune the model consist of descriptions of activities from Icelandic businesses found in their annual reports.

Quick Start

from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("skatturinn/isat-2008")
model = AutoModelForSequenceClassification.from_pretrained("skatturinn/isat-2008")

pl = pipeline(
    "text-classification",
    model=model,
    tokenizer=tokenizer,
    return_all_scores=False,
)

pl("Ég er smiður og ætla mér að smíða hús")