File size: 5,081 Bytes
83daab2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
import os
import json
import random
from tqdm import tqdm
from itertools import islice
from datasets import load_dataset

from typing import List


# Kazakh Cyrillic character to the Kazakh Latin character mapping from 2021 onwards
cyrillic_to_latin = {
    "А": "A", "а": "a",
    "Ә": "Ä", "ә": "ä",
    "Б": "B", "б": "b",
    "Д": "D", "д": "d",
    "Е": "E", "е": "e",
    "Ф": "F", "ф": "f",
    "Г": "G", "г": "g",
    "Ғ": "Ğ", "ғ": "ğ",
    "Х": "H", "х": "h",      # also Һ, see below
    "Һ": "H", "һ": "h",

    "И": "I", "и": "i",      # used for [и], [й]
    "І": "I", "і": "ı",      # distinct from И in sound, both map to 'I/i'
    "Ж": "J", "ж": "j",

    "К": "K", "к": "k",
    "Қ": "Q", "қ": "q",
    "Л": "L", "л": "l",
    "М": "M", "м": "m",
    "Н": "N", "н": "n",
    "Ң": "Ñ", "ң": "ñ",

    "О": "O", "о": "o",
    "Ө": "Ö", "ө": "ö",

    "П": "P", "п": "p",
    "Р": "R", "р": "r",
    "С": "S", "с": "s",
    "Ш": "Ş", "ш": "ş",
    "Т": "T", "т": "t",

    "У": "U", "у": "u",      # basic 'u' sound, distinct from Ұ
    "Ұ": "Ū", "ұ": "ū",      # back rounded, used frequently
    "Ү": "Ü", "ү": "ü",      # front rounded

    "В": "V", "в": "v",
    "Ы": "Y", "ы": "y",
    "Й": "I", "й": "i",      # same treatment as И
    "Ц": "Ts", "ц": "ts",    # for Russian borrowings
    "Ч": "Ch", "ч": "ch",
    "Щ": "Ş", "щ": "ş",      # typically simplified to 'ş'

    "Э": "E", "э": "e",
    "Ю": "Iu", "ю": "iu",    # borrowed words only
    "Я": "Ia", "я": "ia",

    "Ъ": "", "ъ": "",
    "Ь": "", "ь": "",

    "З": "Z", "з": "z",

    # Additional (not in table but used in borrowings)
    "Ё": "Io", "ё": "io",
}


def convert_to_latin(text: str) -> str:
    """
    Simple function to apply the Cyrillic -> Latin mapping for Kazakh characters.
    """
    return ''.join(cyrillic_to_latin.get(char, char) for char in text)


def create_augmented_pairs(sentences: List) -> List:
    """
    Create Kazakh Latin pairs between original sentences and slightly changed ones.
    """
    pairs = []

    # Randomly change sentences
    for _ in range(len(sentences)):
        s = random.choice(sentences)

        # Create a minor variation
        s_aug = s.replace(".", "").replace(",", "")  # remove punctuation
        s_aug = s_aug.replace("ğa", "ga").replace("ñ", "n")  # light spelling variants
        s_aug = s_aug.capitalize()

        if s != s_aug:
            pairs.append({"texts": [s, s_aug]})

    return pairs


# Process all files in "extracted" dir
# Output file path
output_path = "src/data/kazakh_latin_pairs.jsonl"

# List to hold all Latin sentences
latin_sentences = []

# First step: process the Wikipedia dump
print("Processing the Wikipedia dump of Kazakh articles...")

# Iterate over all folders
for root, _, files in os.walk("src/data/extracted"):
    for fname in tqdm(files, desc = "Files in Wikipedia dump"):
        with open(os.path.join(root, fname), 'r', encoding = "utf-8") as f:
            for line in f:
                try:
                    data = json.loads(line)
                    cyr_text = data["text"].strip()
                    lat_text = convert_to_latin(cyr_text).strip()

                    if lat_text:
                        latin_sentences.append(lat_text)

                except Exception as e:
                    tqdm.write(f"Skipping due to: {e}")

                    continue

print("Done")

# Second step: process the "CC100-Kazakh" dataset
print("Loading 'CC100-Kazakh' dataset...")

with open("src/data/kk.txt", 'r', encoding = "utf-8") as f:
    for line in tqdm(islice(f, 50_000), total = 50_000, desc = "Lines in CC100-Kazakh"):
        try:
            cyr_text = line.strip()
            lat_text = convert_to_latin(cyr_text).strip()

            if lat_text:
                latin_sentences.append(lat_text)

        except Exception as e:
            tqdm.write(f"Skipping due to: {e}")

            continue

# Third step: process 15% of the raw, Kazakh-centred part of the "KazParC" dataset
print("Loading 'KazParC' dataset...")

kazparc = load_dataset("issai/kazparc", "kazparc_raw", split = "train[:15%]")

for entry in tqdm(kazparc, desc = "Entries in KazParC"):
    try:
        if "kk" in entry and isinstance(entry["kk"], str):
            cyr_text = entry["kk"].strip()
            lat_text = convert_to_latin(cyr_text).strip()

            if lat_text:
                latin_sentences.append(lat_text)

    except Exception as e:
        tqdm.write(f"Skipping due to: {e}")

        continue


# Fourth and last step: create Latin sentences with variations
print("Creating Latin pairs...")

augmented_pairs = create_augmented_pairs(latin_sentences)

with open(output_path, 'w', encoding = "utf-8") as f:
    for pair in tqdm(augmented_pairs, desc = "Dataset entries"):
        try:
            f.write(json.dumps(pair, ensure_ascii = False) + "\n")

        except Exception as e:
            tqdm.write(f"Skipping due to: {e}")

            continue