Smaller LaBSE

🚀 Smaller LaBSE

Smaller LaBSE is a distilled BERT-based model for multilingual sentence similarity, supporting 15 languages.

🚀 Quick Start

The Smaller Language-agnostic BERT Sentence Encoder (LaBSE) is a BERT-based model. It's distilled from the original LaBSE model to 15 languages (from the original 109 languages). The distillation techniques are described in the paper 'Load What You Need: Smaller Versions of Multilingual BERT' by Ukjae Jeong.

• Model: HuggingFace's model hub.
• Original model: TensorFlow Hub.
• Distillation source: GitHub.
• Conversion from TensorFlow to PyTorch: GitHub.

✨ Features

• Multilingual Support: Supports 15 languages including Arabic, German, English, Spanish, French, Italian, Japanese, Korean, Dutch, Polish, Portuguese, Russian, Thai, Turkish, and Chinese.
• Sentence Similarity: Ideal for calculating sentence similarity across multiple languages.

💻 Usage Examples

Basic Usage

import torch
from transformers import BertModel, BertTokenizerFast


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

Getting Sentence Embeddings

english_embeddings = english_outputs.pooler_output

Output for Other Languages

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

Calculating Sentence 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))

📚 Documentation

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

BibTeX entry and citation info

@misc{feng2020languageagnostic,
      title={Language-agnostic BERT Sentence Embedding},
      author={Fangxiaoyu Feng and Yinfei Yang and Daniel Cer and Naveen Arivazhagan and Wei Wang},
      year={2020},
      eprint={2007.01852},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

📄 License

This model is licensed under the apache-2.0 license.