英文

Multilingual-E5-base

Text Embeddings by Weakly-Supervised Contrastive Pre-training .梁王,南阳,黄小龙,焦彬星,杨琳军,江大新,拉甘·马朱姆德,韦魁富,arXiv 2022

这个模型有12层,嵌入大小为768。

用法

以下是从MS-MARCO通行证排名数据集中编码查询和段落的示例。

import torch.nn.functional as F

from torch import Tensor
from transformers import AutoTokenizer, AutoModel


def average_pool(last_hidden_states: Tensor,
                 attention_mask: Tensor) -> Tensor:
    last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
    return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]


# Each input text should start with "query: " or "passage: ", even for non-English texts.
# For tasks other than retrieval, you can simply use the "query: " prefix.
input_texts = ['query: how much protein should a female eat',
               'query: 南瓜的家常做法',
               "passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 is 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or training for a marathon. Check out the chart below to see how much protein you should be eating each day.",
               "passage: 1.清炒南瓜丝 原料:嫩南瓜半个 调料:葱、盐、白糖、鸡精 做法: 1、南瓜用刀薄薄的削去表面一层皮,用勺子刮去瓤 2、擦成细丝(没有擦菜板就用刀慢慢切成细丝) 3、锅烧热放油,入葱花煸出香味 4、入南瓜丝快速翻炒一分钟左右,放盐、一点白糖和鸡精调味出锅 2.香葱炒南瓜 原料:南瓜1只 调料:香葱、蒜末、橄榄油、盐 做法: 1、将南瓜去皮,切成片 2、油锅8成热后,将蒜末放入爆香 3、爆香后,将南瓜片放入,翻炒 4、在翻炒的同时,可以不时地往锅里加水,但不要太多 5、放入盐,炒匀 6、南瓜差不多软和绵了之后,就可以关火 7、撒入香葱,即可出锅"]

tokenizer = AutoTokenizer.from_pretrained('intfloat/multilingual-e5-base')
model = AutoModel.from_pretrained('intfloat/multilingual-e5-base')

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = average_pool(outputs.last_hidden_state, batch_dict['attention_mask'])

# normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:2] @ embeddings[2:].T) * 100
print(scores.tolist())

支持的语言

此模型从 xlm-roberta-base 中初始化,并在混合多语言数据集上进行连续训练。它支持xlm-roberta的100种语言,但低资源语言可能会出现性能下降。

培训细节

初始化: xlm-roberta-base

第一阶段: 对比预训练,弱监督

Dataset Weak supervision # of text pairs
Filtered 1236321 (title, page content) 1B
1237321 (title, news content) 400M
1238321 translation pairs 2.4B
1239321 (hierarchical section title, passage) 150M
Filtered 12310321 (comment, response) 800M
12311321 (title, abstract) and citation pairs 100M
12312321 (question, answer) 50M
12313321 (input prompt, response) 80M
12314321 - 10M

第二阶段: 监督微调

Dataset Language # of text pairs
12315321 English 500k
12316321 English 70k
12317321 English 60k
12318321 English <300k
12319321 English 500k
12320321 Chinese 86k
12321321 English 70k
12322321 English 70k
12323321 English 87k
12324321 English 150k
12325321 11 languages 50k
12326321 16 languages 40k

对于所有标记的数据集,我们只使用其训练集进行微调。

其他培训细节,请参阅我们在 https://arxiv.org/pdf/2212.03533.pdf 中的论文。

Mr. TyDi 上的基准结果

Model Avg MRR@10 ar bn en fi id ja ko ru sw te th
BM25 33.3 36.7 41.3 15.1 28.8 38.2 21.7 28.1 32.9 39.6 42.4 41.7
mDPR 16.7 26.0 25.8 16.2 11.3 14.6 18.1 21.9 18.5 7.3 10.6 13.5
BM25 + mDPR 41.7 49.1 53.5 28.4 36.5 45.5 35.5 36.2 42.7 40.5 42.0 49.2
multilingual-e5-small 64.4 71.5 66.3 54.5 57.7 63.2 55.4 54.3 60.8 65.4 89.1 70.1
multilingual-e5-base 65.9 72.3 65.0 58.5 60.8 64.9 56.6 55.8 62.7 69.0 86.6 72.7
multilingual-e5-large 70.5 77.5 73.2 60.8 66.8 68.5 62.5 61.6 65.8 72.7 90.2 76.2

MTEB基准评估

查看 unilm/e5 以重现在 BEIR MTEB benchmark 上的评估结果。

Sentence Transformers的支持

以下是与sentence_transformers一起使用的示例。

from sentence_transformers import SentenceTransformer
model = SentenceTransformer('intfloat/multilingual-e5-base')
input_texts = [
    'query: how much protein should a female eat',
    'query: 南瓜的家常做法',
    "passage: As a general guideline, the CDC's average requirement of protein for women ages 19 to 70 i     s 46 grams per day. But, as you can see from this chart, you'll need to increase that if you're expecting or traini     ng for a marathon. Check out the chart below to see how much protein you should be eating each day.",
    "passage: 1.清炒南瓜丝 原料:嫩南瓜半个 调料:葱、盐、白糖、鸡精 做法: 1、南瓜用刀薄薄的削去表面一层皮     ,用勺子刮去瓤 2、擦成细丝(没有擦菜板就用刀慢慢切成细丝) 3、锅烧热放油,入葱花煸出香味 4、入南瓜丝快速翻炒一分钟左右,     放盐、一点白糖和鸡精调味出锅 2.香葱炒南瓜 原料:南瓜1只 调料:香葱、蒜末、橄榄油、盐 做法: 1、将南瓜去皮,切成片 2、油     锅8成热后,将蒜末放入爆香 3、爆香后,将南瓜片放入,翻炒 4、在翻炒的同时,可以不时地往锅里加水,但不要太多 5、放入盐,炒匀      6、南瓜差不多软和绵了之后,就可以关火 7、撒入香葱,即可出锅"
]
embeddings = model.encode(input_texts, normalize_embeddings=True)

要求软件包

pip install sentence_transformers~=2.2.2

贡献者: michaelfeil

常见问题解答

1. 我需要在输入文本中添加前缀“query:”和“passage:”吗?

是的,这是模型的训练方式,否则性能会下降。

以下是一些经验法则:

  • 对于非对称任务(例如开放式QA中的段落检索,即时信息检索),相应地使用“query:”和“passage:”

  • 对于对称任务(例如语义相似性,双文本挖掘,近义词检索),使用“query:”前缀

  • 如果要将嵌入用作特征,例如线性探测分类,聚类,则使用“query:”前缀

2. 为什么我的再现结果与模型卡中报告的结果略有不同?

transformers和pytorch的不同版本可能会导致可忽略但非零的性能差异。

引用

如果您发现我们的论文或模型有帮助,请考虑如下引用:

@article{wang2022text,
  title={Text Embeddings by Weakly-Supervised Contrastive Pre-training},
  author={Wang, Liang and Yang, Nan and Huang, Xiaolong and Jiao, Binxing and Yang, Linjun and Jiang, Daxin and Majumder, Rangan and Wei, Furu},
  journal={arXiv preprint arXiv:2212.03533},
  year={2022}
}

限制

长文本将被截断为最多512个令牌。