File size: 4,017 Bytes
92e884b
 
 
 
 
 
 
 
 
346e7c2
84b9668
b829e56
92e884b
 
 
 
 
 
 
 
 
 
 
 
 
906b46b
92e884b
 
 
 
 
 
 
 
 
 
 
9d2d46c
 
 
 
92e884b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9d2d46c
92e884b
 
 
9d2d46c
906b46b
92e884b
 
 
 
 
74c9273
906b46b
92e884b
 
 
 
 
9d2d46c
 
 
 
 
 
 
8c90d60
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
---
inference: false
license: cc-by-4.0
language:
- bg
metrics:
- accuracy
---

# 🇧🇬 KeyBERT-BG - Bulgarian Keyword Extraction
KeyBERT-BG is a model trained for keyword extraction in Bulgarian.
The used dataset is [this](https://www.kaggle.com/datasets/auhide/bulgarian-articles-with-keywords) custom one, which I've uploaded to Kaggle.

## Usage
Import the libraries:
```python
import re
from typing import Dict
from pprint import pprint

from transformers import AutoTokenizer, AutoModelForTokenClassification
```

Firstly, you'll have to define this method, since the text preprocessing is custom and the standard `pipeline` method won't suffice:
```python
def extract_keywords(
    text: str, 
    model_id="auhide/keybert-bg", 
    max_len: int = 300,
    id2group: Dict[int, str] = {
        # Indicates that this is not a keyword.
        0: "O",
        # Begining of keyword.
        1: "B-KWD",
        # Additional keywords (might also indicate the end of a keyword sequence).
        # You can merge these with the begining keyword `B-KWD`.
        2: "I-KWD",
    },
    # Probability threshold based on which the keywords will be accepted.
    # If their probabiliy is less than `threshold`, they won't be added to the list of keywords.
    threshold=0.50
):
    # Initialize the tokenizer and model.
    tokenizer = AutoTokenizer.from_pretrained(model_id)
    keybert = AutoModelForTokenClassification.from_pretrained(model_id)

    # Preprocess the text.
    # Surround punctuation with whitespace and convert multiple whitespaces
    # into single ones.
    text = re.sub(r"([,\.?!;:\'\"\(\)\[\]„”])", r" \1 ", text)
    text = re.sub(r"\s+", r" ", text)
    words = text.split()

    # Tokenize the processed `text` (this includes padding or truncation).
    tokens_data = tokenizer(
        text.strip(), 
        padding="max_length", 
        max_length=max_len, 
        truncation=True, 
        return_tensors="pt"
    )
    input_ids = tokens_data.input_ids
    attention_mask = tokens_data.attention_mask

    # Predict the keywords.
    out = keybert(input_ids, attention_mask=attention_mask).logits
    # Softmax the last dimension so that the probabilities add up to 1.0.
    out = out.softmax(-1)
    # Based on the probabilities, generate the most probable keywords.
    out_argmax = out.argmax(-1)
    prediction = out_argmax.squeeze(0).tolist()
    probabilities = out.squeeze(0)
    
    return [
        {
            # Since the list of words does not have a [CLS] token, the index `i`
            # is one step forward, which means that if we want to access the 
            # appropriate keyword we should use the index `i - 1`.
            "entity": words[i - 1],
            "entity_group": id2group[idx],
            "score": float(probabilities[i, idx])
        } 
        for i, idx in enumerate(prediction) 
        if (idx == 1 or idx == 2) and float(probabilities[i, idx]) > threshold
    ]
```

Choose a text and use the model on it. For example, I've chosen to use [this](https://novini.bg/biznes/biznes_tehnologii/781108) article.
Then, you can call `extract_keywords` on it and extract its keywords:
```python
# Reading the text from a file, since it is an article, and the text is large.
with open("input_text.txt", "r", encoding="utf-8") as f:
    text = f.read()

# You can change the threshold based on your needs.
keywords = extract_keywords(text, threshold=0.5)
print("Keywords:")
pprint(keywords)
```
```sh
Keywords:
[{'entity': 'Туитър', 'entity_group': 'B-KWD', 'score': 0.9278278946876526},
 {'entity': 'Илон', 'entity_group': 'B-KWD', 'score': 0.5862686634063721},
 {'entity': 'Мъск', 'entity_group': 'B-KWD', 'score': 0.5289096832275391},
 {'entity': 'изпълнителен',
  'entity_group': 'B-KWD',
  'score': 0.679943323135376},
 {'entity': 'директор', 'entity_group': 'I-KWD', 'score': 0.6161141991615295}]
```

Please note that you can use the `pipeline` method from `transformers` but the results would be worse.