metadata

pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - feature-extraction
  - sentence-similarity

ko-sbert-nli

This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.

Usage (Sentence-Transformers)

모델을 사용하기 위해서는 ko-sentence-transformers 를 설치해야 합니다.

pip install -U ko-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('ko-sbert-nli')
embeddings = model.encode(sentences)
print(embeddings)

Evaluation Results

KorNLI 학습 데이터셋으로 학습한 후 KorSTS 평가 데이터셋으로 평가한 결과입니다.

Cosine Pearson: 82.03
Cosine Spearman: 82.36
Euclidean Pearson: 80.06
Euclidean Spearman: 79.85
Manhattan Pearson: 80.08
Manhattan Spearman: 79.91
Dot Pearson: 75.76
Dot Spearman: 74.72

Training

The model was trained with the parameters:

DataLoader:

sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader of length 8886 with parameters:

{'batch_size': 64}

Loss:

sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss with parameters:

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

Parameters of the fit()-Method:

{
    "epochs": 1,
    "evaluation_steps": 888,
    "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
}

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 75, '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)
Ko-Sentence-BERT-SKTBERT
KoBERT