LEALLA Large

🚀 LEALLA-large

LEALLA是一組輕量級的語言無關句子嵌入模型，支持109種語言。它從LaBSE中提煉而來，可用於獲取多語言句子嵌入和雙語文本檢索。

🚀 快速開始

模型信息

• 模型：HuggingFace模型庫。
• 論文：arXiv。
• 原始模型：TensorFlow Hub。
• 從TensorFlow轉換為PyTorch：GitHub。

此模型從TF Hub的v1模型遷移而來。該模型兩個版本生成的嵌入是等效的。不過，對於某些語言（如日語），LEALLA模型在比較嵌入和相似度時似乎需要更高的容差。

模型使用

基礎用法

import torch
from transformers import BertModel, BertTokenizerFast


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

獲取句子嵌入

要獲取句子嵌入，請使用池化器輸出：

english_embeddings = english_outputs.pooler_output

其他語言的輸出

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

句子相似度計算

在計算相似度之前，建議對嵌入進行L2歸一化：

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))

📚 詳細文檔

關於數據、訓練、評估和性能指標的詳細信息，請參考原始論文。

📄 許可證

本項目採用Apache-2.0許可證。

📑 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.",
}

📋 模型信息表格