ko-sbert-sts

Usage (Sentence-Transformers)

Using this model becomes easy when you have sentence-transformers installed:

pip install -U sentence-transformers

Then you can use the model like this:

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)

Usage (HuggingFace Transformers)

Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.

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)

Evaluation Results

KorSTS 학습 데이터셋으로 학습한 후 KorSTS 평가 데이터셋으로 평가한 결과입니다.

• Cosine Pearson: 81.55
• Cosine Spearman: 81.23
• Euclidean Pearson: 79.94
• Euclidean Spearman: 79.79
• Manhattan Pearson: 79.90
• Manhattan Spearman: 79.75
• Dot Pearson: 76.02
• Dot Spearman: 75.31

Training

The model was trained with the parameters:

DataLoader:

torch.utils.data.dataloader.DataLoader of length 719 with parameters:

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

Loss:

sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss

Parameters of the fit()-Method:

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

Full Model Architecture

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})
)

Citing & Authors

• 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)