robbert 2022 dutch sentence transformers EU AI Act Compliance Profile

robbert-2022-dutch-sentence-transformers

This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.

This model is based on KU Leuven's RobBERT model. It has been finetuned on the Paraphrase dataset, which we (machine-) translated to Dutch. The Paraphrase dataset consists of multiple datasets that consist of duo's of similar texts, for example duplicate questions on a forum. We have released the translated data that we used to train this model on our Huggingface page.

Usage (Sentence-Transformers)

Using this model becomes easy when you have sentence-transformers installed:

Then you can use the model like this:

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('NetherlandsForensicInstitute/robbert-2022-dutch-sentence-transformers')
embeddings = model.encode(sentences)
print(embeddings)

Usage (HuggingFace Transformers)

Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.

from transformers import AutoTokenizer, AutoModel
import torch


#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.siz

Your obligations as a robbert 2022 dutch sentence transformers deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Languages

Library

Base Model