Edit model card


Model description

Language-agnostic BERT Sentence Encoder (LaBSE) is a BERT-based model trained for sentence embedding for 109 languages. The pre-training process combines masked language modeling with translation language modeling. The model is useful for getting multilingual sentence embeddings and for bi-text retrieval.

This is migrated from the v2 model on the TF Hub, which uses dict-based input. The embeddings produced by both the versions of the model are equivalent.


Using the model:

import torch
from transformers import BertModel, BertTokenizerFast

tokenizer = BertTokenizerFast.from_pretrained("setu4993/LaBSE")
model = BertModel.from_pretrained("setu4993/LaBSE")
model = model.eval()

english_sentences = [
    "Puppies are nice.",
    "I enjoy taking long walks along the beach with my dog.",
english_inputs = tokenizer(english_sentences, return_tensors="pt", padding=True)

with torch.no_grad():
    english_outputs = model(**english_inputs)

To get the sentence embeddings, use the pooler output:

english_embeddings = english_outputs.pooler_output

Output for other languages:

italian_sentences = [
    "I cuccioli sono carini.",
    "Mi piace fare lunghe passeggiate lungo la spiaggia con il mio cane.",
japanese_sentences = ["็Šฌ", "ๅญ็Šฌใฏใ„ใ„ใงใ™", "็งใฏ็Šฌใจไธ€็ท’ใซใƒ“ใƒผใƒใ‚’ๆ•ฃๆญฉใ™ใ‚‹ใฎใŒๅฅฝใใงใ™"]
italian_inputs = tokenizer(italian_sentences, return_tensors="pt", padding=True)
japanese_inputs = tokenizer(japanese_sentences, return_tensors="pt", padding=True)

with torch.no_grad():
    italian_outputs = model(**italian_inputs)
    japanese_outputs = model(**japanese_inputs)

italian_embeddings = italian_outputs.pooler_output
japanese_embeddings = japanese_outputs.pooler_output

For similarity between sentences, an L2-norm is recommended before calculating the similarity:

import torch.nn.functional as F

def similarity(embeddings_1, embeddings_2):
    normalized_embeddings_1 = F.normalize(embeddings_1, p=2)
    normalized_embeddings_2 = F.normalize(embeddings_2, p=2)
    return torch.matmul(
        normalized_embeddings_1, normalized_embeddings_2.transpose(0, 1)

print(similarity(english_embeddings, italian_embeddings))
print(similarity(english_embeddings, japanese_embeddings))
print(similarity(italian_embeddings, japanese_embeddings))


Details about data, training, evaluation and performance metrics are available in the original paper.

BibTeX entry and citation info

      title={Language-agnostic BERT Sentence Embedding},
      author={Fangxiaoyu Feng and Yinfei Yang and Daniel Cer and Naveen Arivazhagan and Wei Wang},
Downloads last month
Model size
471M params
Tensor type
Inference Examples
Inference API (serverless) does not yet support transformers models for this pipeline type.

Spaces using setu4993/LaBSE 6