LEALLA Base

🚀 LEALLA-base

LEALLA是一组轻量级、与语言无关的句子嵌入模型，支持109种语言。它从LaBSE模型中提炼而来，可用于获取多语言句子嵌入和双语文本检索。

🚀 快速开始

LEALLA是一个支持109种语言的轻量级语言无关句子嵌入模型集合，从LaBSE中蒸馏而来。该模型可用于获取多语言句子嵌入和进行双语文本检索。

• 模型：HuggingFace模型库
• 论文：arXiv
• 原始模型：TensorFlow Hub
• 从TensorFlow转换为PyTorch：GitHub

此模型从TF Hub上的v1模型迁移而来。两个版本模型生成的嵌入是等效的。不过，对于某些语言（如日语），LEALLA模型在比较嵌入和相似度时似乎需要更高的容差。

✨ 主要特性

• 多语言支持：支持多达109种语言，包括但不限于英语、意大利语、日语等。
• 轻量级：基于知识蒸馏技术，模型轻量，减少推理速度和计算开销。
• 语言无关：能够生成与语言无关的句子嵌入，适用于跨语言任务。

📦 安装指南

文档未提及具体安装步骤，可参考以下通用步骤：

pip install transformers torch

💻 使用示例

基础用法

import torch
from transformers import BertModel, BertTokenizerFast

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

获取句子嵌入

english_embeddings = english_outputs.pooler_output

其他语言输出示例

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

计算句子相似度

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))

📚 详细文档

有关数据、训练、评估和性能指标的详细信息，请参阅原始论文。

🔧 技术细节

BibTeX引用和引用信息

@inproceedings{mao-nakagawa-2023-lealla,
    title = "{LEALLA}: Learning Lightweight Language-agnostic Sentence Embeddings with Knowledge Distillation",
    author = "Mao, Zhuoyuan  and
      Nakagawa, Tetsuji",
    booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
    month = may,
    year = "2023",
    address = "Dubrovnik, Croatia",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.eacl-main.138",
    doi = "10.18653/v1/2023.eacl-main.138",
    pages = "1886--1894",
    abstract = "Large-scale language-agnostic sentence embedding models such as LaBSE (Feng et al., 2022) obtain state-of-the-art performance for parallel sentence alignment. However, these large-scale models can suffer from inference speed and computation overhead. This study systematically explores learning language-agnostic sentence embeddings with lightweight models. We demonstrate that a thin-deep encoder can construct robust low-dimensional sentence embeddings for 109 languages. With our proposed distillation methods, we achieve further improvements by incorporating knowledge from a teacher model. Empirical results on Tatoeba, United Nations, and BUCC show the effectiveness of our lightweight models. We release our lightweight language-agnostic sentence embedding models LEALLA on TensorFlow Hub.",
}

📄 许可证

本项目采用Apache-2.0许可证。