Ko Sroberta Nli

🚀 韓語語義相似度模型 - ko-sroberta-nli

本模型基於 sentence-transformers 構建，它能夠將句子和段落映射到 768 維的密集向量空間，可用於聚類、語義搜索等任務。

🚀 快速開始

📦 安裝依賴

若已安裝 sentence-transformers，使用本模型將十分便捷：

pip install -U sentence-transformers

💻 使用示例

基礎用法（使用 sentence-transformers 庫）

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

model = SentenceTransformer('jhgan/ko-sroberta-nli')
embeddings = model.encode(sentences)
print(embeddings)

高級用法（使用 HuggingFace Transformers 庫）

若未安裝 sentence-transformers，可以按以下步驟使用模型：首先，將輸入數據傳入 Transformer 模型，然後對上下文詞嵌入應用合適的池化操作。

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-sroberta-nli')
model = AutoModel.from_pretrained('jhgan/ko-sroberta-nli')

# 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)

📊 評估結果

本模型在 KorNLI 訓練數據集上進行訓練，並在 KorSTS 評估數據集上進行評估，結果如下：

🔧 訓練細節

本模型的訓練參數如下：

數據加載器

sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader，長度為 8885，參數如下：

{'batch_size': 64}

損失函數

sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss，參數如下：

{'scale': 20.0, 'similarity_fct': 'cos_sim'}

fit() 方法的參數

{
    "epochs": 1,
    "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": 889,
    "weight_decay": 0.01
}

📚 完整模型架構

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: RobertaModel 
  (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})
)

📄 引用與作者

• Ham, J., Choe, Y. J., Park, K., Choi, I., & Soh, H. (2020). Kornli and korsts: New benchmark datasets for korean natural language understanding. arXiv preprint 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).