ko-sbert-sts

这是一个 sentence-transformers 模型：它将句子和段落映射到一个768维的稠密向量空间，可用于聚类或语义搜索等任务。

用法（Sentence-Transformers）

当您安装了 sentence-transformers 后，使用这个模型变得很容易：

pip install -U sentence-transformers

然后您可以像这样使用模型：

from sentence_transformers import SentenceTransformer
sentences = ["안녕하세요?", "한국어 문장 임베딩을 위한 버트 모델입니다."]

model = SentenceTransformer('jhgan/ko-sbert-sts')
embeddings = model.encode(sentences)
print(embeddings)

用法（HuggingFace Transformers）

如果没有 sentence-transformers ，您可以像这样使用模型：首先，将输入传递给变换器模型，然后必须在上下文化的词嵌入之上应用正确的汇聚操作。

from transformers import AutoTokenizer, AutoModel
import torch


#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)


# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('jhgan/ko-sbert-sts')
model = AutoModel.from_pretrained('jhgan/ko-sbert-sts')

# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)

# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

print("Sentence embeddings:")
print(sentence_embeddings)

评估结果

这是使用KorSTS训练数据集进行训练，然后在KorSTS评估数据集上评估的结果。

• 余弦Pearson系数：81.55
• 余弦Spearman系数：81.23
• 欧几里德Pearson系数：79.94
• 欧几里德Spearman系数：79.79
• 曼哈顿Pearson系数：79.90
• 曼哈顿Spearman系数：79.75
• 点积Pearson系数：76.02
• 点积Spearman系数：75.31

训练

该模型使用以下参数进行训练：

数据加载器：

torch.utils.data.dataloader.DataLoader，长度为719，参数如下：

{'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

损失函数：

sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss

fit()方法的参数：

{
    "epochs": 5,
    "evaluation_steps": 1000,
    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 360,
    "weight_decay": 0.01
}

完整的模型架构

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

引用和作者

• Ham, J., Choe, Y. J., Park, K., Choi, I., & Soh, H. (2020). Kornli and korsts: New benchmark datasets for korean natural language understanding. arXivpreprint arXiv:2004.03289
• Reimers, Nils and Iryna Gurevych. “Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.” ArXiv abs/1908.10084 (2019)
• Reimers, Nils and Iryna Gurevych. “Making Monolingual Sentence Embeddings Multilingual Using Knowledge Distillation.” EMNLP (2020)