LEALLA-small

Model description

LEALLA is a collection of lightweight language-agnostic sentence embedding models supporting 109 languages, distilled from LaBSE . The model is useful for getting multilingual sentence embeddings and for bi-text retrieval.

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

This is migrated from the v1 model on the TF Hub. The embeddings produced by both the versions of the model are equivalent . Though, for some of the languages (like Japanese), the LEALLA models appear to require higher tolerances when comparing embeddings and similarities.

Usage

Using the model:

import torch
from transformers import BertModel, BertTokenizerFast


tokenizer = BertTokenizerFast.from_pretrained("setu4993/LEALLA-small")
model = BertModel.from_pretrained("setu4993/LEALLA-small")
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:

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

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

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

BibTeX entry and citation info

@misc{mao2023lealla,
      title={LEALLA: Learning Lightweight Language-agnostic Sentence Embeddings with Knowledge Distillation},
      author={Zhuoyuan Mao and Tetsuji Nakagawa},
      year={2023},
      eprint={2302.08387},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}