Update README.md
Browse files
README.md
CHANGED
|
@@ -29,16 +29,17 @@ sentence-similarityλ₯Ό ꡬνλ μ©λλ‘ λ°λ‘ μ¬μ©ν μλ μκ³ , λͺ©
|
|
| 29 |
|
| 30 |
## Usage (Sentence-Transformers)
|
| 31 |
|
| 32 |
-
|
| 33 |
|
| 34 |
```
|
| 35 |
pip install -U sentence-transformers
|
| 36 |
```
|
| 37 |
|
| 38 |
-
|
| 39 |
|
| 40 |
```python
|
| 41 |
from sentence_transformers import SentenceTransformer
|
|
|
|
| 42 |
sentences = ["This is an example sentence", "Each sentence is converted"]
|
| 43 |
|
| 44 |
model = SentenceTransformer('smartmind/roberta-ko-small-tsdae')
|
|
@@ -46,10 +47,41 @@ embeddings = model.encode(sentences)
|
|
| 46 |
print(embeddings)
|
| 47 |
```
|
| 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
|
| 50 |
|
| 51 |
## Usage (HuggingFace Transformers)
|
| 52 |
-
|
|
|
|
| 53 |
|
| 54 |
```python
|
| 55 |
from transformers import AutoTokenizer, AutoModel
|
|
@@ -103,4 +135,4 @@ SentenceTransformer(
|
|
| 103 |
|
| 104 |
## Citing & Authors
|
| 105 |
|
| 106 |
-
<!--- Describe where people can find more information -->
|
|
|
|
| 29 |
|
| 30 |
## Usage (Sentence-Transformers)
|
| 31 |
|
| 32 |
+
[sentence-transformers](https://www.SBERT.net)λ₯Ό μ€μΉν λ€, λͺ¨λΈμ λ°λ‘ λΆλ¬μ¬ μ μμ΅λλ€.
|
| 33 |
|
| 34 |
```
|
| 35 |
pip install -U sentence-transformers
|
| 36 |
```
|
| 37 |
|
| 38 |
+
μ΄ν λ€μμ²λΌ λͺ¨λΈμ μ¬μ©ν μ μμ΅λλ€.
|
| 39 |
|
| 40 |
```python
|
| 41 |
from sentence_transformers import SentenceTransformer
|
| 42 |
+
|
| 43 |
sentences = ["This is an example sentence", "Each sentence is converted"]
|
| 44 |
|
| 45 |
model = SentenceTransformer('smartmind/roberta-ko-small-tsdae')
|
|
|
|
| 47 |
print(embeddings)
|
| 48 |
```
|
| 49 |
|
| 50 |
+
λ€μμ sentence-transformersμ κΈ°λ₯μ μ¬μ©νμ¬ μ¬λ¬ λ¬Έμ₯μ μ μ¬λλ₯Ό ꡬνλ μμμ
λλ€.
|
| 51 |
+
|
| 52 |
+
```python
|
| 53 |
+
from sentence_transformers import util
|
| 54 |
+
|
| 55 |
+
sentences = [
|
| 56 |
+
"λνλ―Όκ΅μ μλλ μμΈμ
λλ€.",
|
| 57 |
+
"λ―Έκ΅μ μλλ λ΄μμ΄ μλλλ€.",
|
| 58 |
+
"λνλ―Όκ΅μ μλ μκΈμ μ λ ΄ν νΈμ
λλ€.",
|
| 59 |
+
"μμΈμ λνλ―Όκ΅μ μλμ
λλ€.",
|
| 60 |
+
"μ€λ μμΈμ ν루μ’
μΌ λ§μ",
|
| 61 |
+
]
|
| 62 |
+
|
| 63 |
+
paraphrase = util.paraphrase_mining(model, sentences)
|
| 64 |
+
for score, i, j in paraphrase:
|
| 65 |
+
print(f"{sentences[i]}\t\t{sentences[j]}\t\t{score:.4f}")
|
| 66 |
+
```
|
| 67 |
+
|
| 68 |
+
```
|
| 69 |
+
λνλ―Όκ΅μ μλλ μμΈμ
λλ€. μμΈμ λνλ―Όκ΅μ μλμ
λλ€. 0.7616
|
| 70 |
+
λνλ―Όκ΅μ μλλ μμΈμ
λλ€. λ―Έκ΅μ μλλ λ΄μμ΄ μλλλ€. 0.7031
|
| 71 |
+
λνλ―Όκ΅μ μλλ μμΈμ
λλ€. λνλ―Όκ΅μ μλ μκΈμ μ λ ΄ν νΈμ
λλ€. 0.6594
|
| 72 |
+
λ―Έκ΅μ μλλ λ΄μμ΄ μλλλ€. μμΈμ λνλ―Όκ΅μ μλμ
λλ€. 0.6445
|
| 73 |
+
λνλ―Όκ΅μ μλ μκΈμ μ λ ΄ν νΈμ
λλ€. μμΈμ λνλ―Όκ΅μ μλμ
λλ€. 0.4915
|
| 74 |
+
λ―Έκ΅μ μλλ λ΄μμ΄ μλλλ€. λνλ―Όκ΅μ μλ μκΈμ μ λ ΄ν νΈμ
λλ€. 0.4785
|
| 75 |
+
μμΈμ λνλ―Όκ΅μ μλμ
λλ€. μ€λ μμΈμ ν루μ’
μΌ λ§μ 0.4119
|
| 76 |
+
λνλ―Όκ΅μ μλλ μμΈμ
λλ€. μ€λ μμΈμ ν루μ’
μΌ λ§μ 0.3520
|
| 77 |
+
λ―Έκ΅μ μλλ λ΄μμ΄ μλλλ€. μ€λ μμΈμ ν루μ’
μΌ λ§μ 0.2550
|
| 78 |
+
λνλ―Όκ΅μ μλ μκΈμ μ λ ΄ν νΈμ
λλ€. μ€λ μμΈμ ν루μ’
μΌ λ§μ 0.1896
|
| 79 |
+
```
|
| 80 |
|
| 81 |
|
| 82 |
## Usage (HuggingFace Transformers)
|
| 83 |
+
|
| 84 |
+
[sentence-transformers](https://www.SBERT.net)λ₯Ό μ€μΉνμ§ μμ μνλ‘λ λ€μμ²λΌ μ¬μ©ν μ μμ΅λλ€.
|
| 85 |
|
| 86 |
```python
|
| 87 |
from transformers import AutoTokenizer, AutoModel
|
|
|
|
| 135 |
|
| 136 |
## Citing & Authors
|
| 137 |
|
| 138 |
+
<!--- Describe where people can find more information -->
|