LaBSE的副本，返回句子嵌入（pooler_output）并实现缓存

原模型卡片：

LaBSE

模型描述

语言不可知的BERT句子编码器（LaBSE）是一个基于BERT训练的模型，用于109种语言的句子嵌入。预训练过程将掩码语言建模与翻译语言建模相结合。该模型可用于获取多语言句子嵌入和双文本检索。

• 模型： HuggingFace's model hub .
• 论文： arXiv .
• 原始模型： TensorFlow Hub .
• 博文： Google AI Blog .
• 从TensorFlow转换到PyTorch： GitHub .

该模型是从TF Hub的v2模型迁移而来，使用基于字典的输入。两个版本的模型产生的嵌入是 equivalent .

用法

使用模型：

import torch
from transformers import BertModel, BertTokenizerFast


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

要获取句子嵌入，请使用池化器输出：

english_embeddings = english_outputs.pooler_output

其他语言的输出：

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

对于句子之间的相似度计算，建议先进行L2范数处理：

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))

详细信息

数据、训练、评估和性能指标的详细信息可在 original paper 中找到。

BibTeX条目和引用信息

@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}
}