|
--- |
|
pipeline_tag: sentence-similarity |
|
tags: |
|
- sentence-transformers |
|
- feature-extraction |
|
- sentence-similarity |
|
--- |
|
|
|
# ko-sbert-sts |
|
|
|
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. |
|
|
|
<!--- Describe your model here --> |
|
|
|
## Usage (Sentence-Transformers) |
|
|
|
๋ชจ๋ธ์ ์ฌ์ฉํ๊ธฐ ์ํด์๋ `ko-sentence-transformers` ๋ฅผ ์ค์นํด์ผ ํฉ๋๋ค. |
|
|
|
``` |
|
pip install -U ko-sentence-transformers |
|
``` |
|
|
|
Then you can use the model like this: |
|
|
|
```python |
|
from sentence_transformers import SentenceTransformer |
|
sentences = ["์๋
ํ์ธ์?", "ํ๊ตญ์ด ๋ฌธ์ฅ ์๋ฒ ๋ฉ์ ์ํ ๋ฒํธ ๋ชจ๋ธ์
๋๋ค."] |
|
|
|
model = SentenceTransformer('jhgan/ko-sbert-sts') |
|
embeddings = model.encode(sentences) |
|
print(embeddings) |
|
``` |
|
|
|
|
|
|
|
## Evaluation Results |
|
|
|
KorSTS ํ์ต ๋ฐ์ดํฐ์
์ผ๋ก ํ์ตํ ํ KorSTS ํ๊ฐ ๋ฐ์ดํฐ์
์ผ๋ก ํ๊ฐํ ๊ฒฐ๊ณผ์
๋๋ค. |
|
|
|
- Cosine Pearson: 80.79 |
|
- Cosine Spearman: 79.01 |
|
- Euclidean Pearson: 78.03 |
|
- Euclidean Spearman: 77.31 |
|
- Manhattan Pearson: 78.08 |
|
- Manhattan Spearman: 77.35 |
|
- Dot Pearson: 75.96 |
|
- Dot Spearman: 75.20 |
|
|
|
## 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": 4, |
|
"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": 288, |
|
"weight_decay": 0.01 |
|
} |
|
``` |
|
|
|
|
|
## Full Model Architecture |
|
``` |
|
SentenceTransformer( |
|
(0): Transformer({'max_seq_length': 512, '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. โSentence-BERT: Sentence Embeddings using Siamese BERT-Networks.โ ArXiv abs/1908.10084 (2019) |
|
- [Ko-Sentence-BERT-SKTBERT](https://github.com/BM-K/KoSentenceBERT-SKT) |
|
- [KoBERT](https://github.com/SKTBrain/KoBERT) |
|
|