---
language:
- multilingual
- af
- sq
- am
- ar
- hy
- as
- az
- eu
- be
- bn
- bs
- bg
- my
- ca
- ceb
- zh
- co
- hr
- cs
- da
- nl
- en
- eo
- et
- fi
- fr
- fy
- gl
- ka
- de
- el
- gu
- ht
- ha
- haw
- he
- hi
- hmn
- hu
- is
- ig
- id
- ga
- it
- ja
- jv
- kn
- kk
- km
- rw
- ko
- ku
- ky
- lo
- la
- lv
- lt
- lb
- mk
- mg
- ms
- ml
- mt
- mi
- mr
- mn
- ne
- no
- ny
- or
- fa
- pl
- pt
- pa
- ro
- ru
- sm
- gd
- sr
- st
- sn
- si
- sk
- sl
- so
- es
- su
- sw
- sv
- tl
- tg
- ta
- tt
- te
- th
- bo
- tr
- tk
- ug
- uk
- ur
- uz
- vi
- cy
- wo
- xh
- yi
- yo
- zu
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
library_name: sentence-transformers
license: apache-2.0
---

# AviLaBSE
This is a port of the [LaBSE](https://tfhub.dev/google/LaBSE/1) model to PyTorch. Language-agnostic BERT Sentence Encoder (LaBSE) is a BERT-based model trained for sentence embedding for 109 languages.  It can be used to map 109 languages to a shared vector space. 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.

- Model: [HuggingFace's model hub](https://huggingface.co/sartifyllc/AviLaBSE).
- Paper: [arXiv](https://arxiv.org/abs/2007.01852).
- Original model: [TensorFlow Hub](https://tfhub.dev/google/LaBSE/2).
- Blog post: [Google AI Blog](https://ai.googleblog.com/2020/08/language-agnostic-bert-sentence.html).
- Conversion from TensorFlow to PyTorch: [GitHub](https://github.com/sartify).

## Usage (Sentence-Transformers)

Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:

```
pip install -U sentence-transformers
```

Then you can use the model like this:

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

model = SentenceTransformer('sartifyllc/AviLaBSE')
embeddings = model.encode(sentences)
print(embeddings)
```

```python
import torch
from transformers import BertModel, BertTokenizerFast

tokenizer = BertTokenizerFast.from_pretrained("sartifyllc/AviLaBSE")
model = BertModel.from_pretrained("sartifyllc/AviLaBSE")
model = model.eval()

english_sentences = [
    "dog",
    "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:

```python
english_embeddings = english_outputs.pooler_output
```

Output for other languages:

```python
italian_sentences = [
    "cane",
    "I cuccioli sono carini.",
    "Mi piace fare lunghe passeggiate lungo la spiaggia con il mio cane.",
]
japanese_sentences = ["犬", "子犬はいいです", "私は犬と一緒にビーチを散歩するのが好きです"]
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:

```python
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))
```



## Evaluation Results



For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/LaBSE)



## Full Model Architecture
```
SentenceTransformer(
  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
  (2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
  (3): Normalize()
)
```

## Citing & Authors

Have a look at [LaBSE](https://tfhub.dev/google/LaBSE/2) for the respective publication that describes LaBSE.