paraphrase-xlm-r-multilingual-v1

Sentence Embeddings Models trained on Paraphrases

This model is from the sentence-transformers-repository. It was trained on millions of paraphrase sentences. Further details on SBERT can be found in the paper: Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

This model is the multilingual version of distilroberta-base-paraphrase-v1, trained on parallel data for 50+ languages.

Usage (HuggingFace Models Repository)

You can use the model directly from the model repository to compute sentence 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.size()).float()
    sum_embeddings = torch.sum(token_embeddings * input_mask_expanded, 1)
    sum_mask = torch.clamp(input_mask_expanded.sum(1), min=1e-9)
    return sum_embeddings / sum_mask



#Sentences we want sentence embeddings for
sentences = ['This framework generates embeddings for each input sentence',
             'Sentences are passed as a list of string.',
             'The quick brown fox jumps over the lazy dog.']

#Load AutoModel from huggingface model repository
tokenizer = AutoTokenizer.from_pretrained("model_name")
model = AutoModel.from_pretrained("model_name")

#Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, max_length=128, return_tensors='pt')

#Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)

#Perform pooling. In this case, mean pooling
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

Usage (Sentence-Transformers)

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

pip install -U sentence-transformers

Then you can use the model like this:

from sentence_transformers import SentenceTransformer
model = SentenceTransformer('model_name')
sentences = ['This framework generates embeddings for each input sentence',
    'Sentences are passed as a list of string.', 
    'The quick brown fox jumps over the lazy dog.']
sentence_embeddings = model.encode(sentences)

print("Sentence embeddings:")
print(sentence_embeddings)

Citing & Authors

If you find this model helpful, feel free to cite our publication Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation:

@inproceedings{reimers-2020-multilingual-sentence-bert,
    title = "Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2020",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/2004.09813",
}
Downloads last month
1,886,737
Hosted inference API
Feature Extraction
This model can be loaded on the Inference API on-demand.