Commit ·
ec36a6d
1
Parent(s): e128e0e
Phase A: Fix verdict logic - strip terminal punctuation before correction comparison
Browse files
tests/v2/debug_verdict.py
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import json
|
| 2 |
+
|
| 3 |
+
d = json.load(open('tests/v2/reports/level3_integrated_results.json', 'r', encoding='utf-8'))
|
| 4 |
+
for r in d['results'][:5]:
|
| 5 |
+
print(f"ID: {r['id']}")
|
| 6 |
+
print(f" IN: {r['input_text']}")
|
| 7 |
+
print(f" EXP: {r['expected']}")
|
| 8 |
+
print(f" OUT: {r['pipeline_corrected']}")
|
| 9 |
+
print(f" V: {r['verdict']} | {r['detail']}")
|
| 10 |
+
print()
|
tests/v2/reports/benchmark_matrix.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"timestamp": "2026-06-23T18:55:12Z",
|
| 3 |
+
"l1_timestamp": null,
|
| 4 |
+
"l2_timestamp": "2026-06-23T18:55:12Z",
|
| 5 |
+
"l3_timestamp": "2026-06-23T18:54:52Z",
|
| 6 |
+
"l2_summary": {
|
| 7 |
+
"spelling": {
|
| 8 |
+
"TP": 0,
|
| 9 |
+
"TN": 19,
|
| 10 |
+
"FP": 11,
|
| 11 |
+
"FN": 0,
|
| 12 |
+
"pass_rate": 0.6333
|
| 13 |
+
},
|
| 14 |
+
"grammar": {
|
| 15 |
+
"TP": 0,
|
| 16 |
+
"TN": 25,
|
| 17 |
+
"FP": 5,
|
| 18 |
+
"FN": 0,
|
| 19 |
+
"pass_rate": 0.8333
|
| 20 |
+
},
|
| 21 |
+
"punctuation": {
|
| 22 |
+
"TP": 0,
|
| 23 |
+
"TN": 1,
|
| 24 |
+
"FP": 29,
|
| 25 |
+
"FN": 0,
|
| 26 |
+
"pass_rate": 0.0333
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"l3_summary": {
|
| 30 |
+
"TP": 22,
|
| 31 |
+
"TN": 0,
|
| 32 |
+
"FP": 58,
|
| 33 |
+
"FN": 0,
|
| 34 |
+
"pass_rate": 0.275
|
| 35 |
+
}
|
| 36 |
+
}
|
tests/v2/reports/level2_solo_results.json
ADDED
|
@@ -0,0 +1,568 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"timestamp": "2026-06-23T18:55:12Z",
|
| 3 |
+
"target": "https://bayan10-bayan-api.hf.space",
|
| 4 |
+
"analysis": {
|
| 5 |
+
"total": 30,
|
| 6 |
+
"by_model": {
|
| 7 |
+
"spelling": {
|
| 8 |
+
"TP": 0,
|
| 9 |
+
"TN": 19,
|
| 10 |
+
"FP": 11,
|
| 11 |
+
"FN": 0,
|
| 12 |
+
"pass_rate": 0.6333
|
| 13 |
+
},
|
| 14 |
+
"grammar": {
|
| 15 |
+
"TP": 0,
|
| 16 |
+
"TN": 25,
|
| 17 |
+
"FP": 5,
|
| 18 |
+
"FN": 0,
|
| 19 |
+
"pass_rate": 0.8333
|
| 20 |
+
},
|
| 21 |
+
"punctuation": {
|
| 22 |
+
"TP": 0,
|
| 23 |
+
"TN": 1,
|
| 24 |
+
"FP": 29,
|
| 25 |
+
"FN": 0,
|
| 26 |
+
"pass_rate": 0.0333
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"by_dataset": {
|
| 30 |
+
"entities": {
|
| 31 |
+
"total": 30,
|
| 32 |
+
"spelling": {
|
| 33 |
+
"TP": 0,
|
| 34 |
+
"TN": 19,
|
| 35 |
+
"FP": 11,
|
| 36 |
+
"FN": 0,
|
| 37 |
+
"pass_rate": 0.6333
|
| 38 |
+
},
|
| 39 |
+
"grammar": {
|
| 40 |
+
"TP": 0,
|
| 41 |
+
"TN": 25,
|
| 42 |
+
"FP": 5,
|
| 43 |
+
"FN": 0,
|
| 44 |
+
"pass_rate": 0.8333
|
| 45 |
+
},
|
| 46 |
+
"punctuation": {
|
| 47 |
+
"TP": 0,
|
| 48 |
+
"TN": 1,
|
| 49 |
+
"FP": 29,
|
| 50 |
+
"FN": 0,
|
| 51 |
+
"pass_rate": 0.0333
|
| 52 |
+
}
|
| 53 |
+
}
|
| 54 |
+
}
|
| 55 |
+
},
|
| 56 |
+
"results": [
|
| 57 |
+
{
|
| 58 |
+
"id": "E001",
|
| 59 |
+
"dataset": "entities",
|
| 60 |
+
"category": "person",
|
| 61 |
+
"input_text": "محمد صلاح لاعب كرة قدم مصري",
|
| 62 |
+
"expected": "محمد صلاح لاعب كرة قدم مصري",
|
| 63 |
+
"severity": "major",
|
| 64 |
+
"spelling_solo": "محمد صلاح لاعب كرة قدم مصري",
|
| 65 |
+
"spelling_ms": 2410,
|
| 66 |
+
"grammar_solo": "محمد صلاح لاعب كرة قدم مصري",
|
| 67 |
+
"grammar_ms": 5530,
|
| 68 |
+
"punctuation_solo": "محمد صلاح لاعب كرة قدم مصري.",
|
| 69 |
+
"punctuation_ms": 5395,
|
| 70 |
+
"spelling_verdict": "TN",
|
| 71 |
+
"grammar_verdict": "TN",
|
| 72 |
+
"punctuation_verdict": "FP"
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"id": "E002",
|
| 76 |
+
"dataset": "entities",
|
| 77 |
+
"category": "person",
|
| 78 |
+
"input_text": "عبدالله يدرس في الجامعة",
|
| 79 |
+
"expected": "عبدالله يدرس في الجامعة",
|
| 80 |
+
"severity": "major",
|
| 81 |
+
"spelling_solo": "عبد الله يدرس في الجامعة",
|
| 82 |
+
"spelling_ms": 5223,
|
| 83 |
+
"grammar_solo": "عبدالله يدرس في الجامعة",
|
| 84 |
+
"grammar_ms": 3398,
|
| 85 |
+
"punctuation_solo": "عبدالله يدرس في الجامعة.",
|
| 86 |
+
"punctuation_ms": 5254,
|
| 87 |
+
"spelling_verdict": "FP",
|
| 88 |
+
"grammar_verdict": "TN",
|
| 89 |
+
"punctuation_verdict": "FP"
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"id": "E003",
|
| 93 |
+
"dataset": "entities",
|
| 94 |
+
"category": "person",
|
| 95 |
+
"input_text": "عبد الرحمن أخي الأكبر",
|
| 96 |
+
"expected": "عبد الرحمن أخي الأكبر",
|
| 97 |
+
"severity": "major",
|
| 98 |
+
"spelling_solo": "عبد الرحمن أخي الأكبر",
|
| 99 |
+
"spelling_ms": 6535,
|
| 100 |
+
"grammar_solo": "عبد الرحمن أخي الأكبر",
|
| 101 |
+
"grammar_ms": 7989,
|
| 102 |
+
"punctuation_solo": "عبد الرحمن أخي الأكبر.",
|
| 103 |
+
"punctuation_ms": 4209,
|
| 104 |
+
"spelling_verdict": "TN",
|
| 105 |
+
"grammar_verdict": "TN",
|
| 106 |
+
"punctuation_verdict": "FP"
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"id": "E004",
|
| 110 |
+
"dataset": "entities",
|
| 111 |
+
"category": "person",
|
| 112 |
+
"input_text": "أحمد محمود يعمل مهندساً",
|
| 113 |
+
"expected": "أحمد محمود يعمل مهندساً",
|
| 114 |
+
"severity": "major",
|
| 115 |
+
"spelling_solo": "أحمد محمود يعمل مهندسا",
|
| 116 |
+
"spelling_ms": 4471,
|
| 117 |
+
"grammar_solo": "أحمد محمود يعمل مهندسا",
|
| 118 |
+
"grammar_ms": 4225,
|
| 119 |
+
"punctuation_solo": "أحمد محمود يعمل مهندساً.",
|
| 120 |
+
"punctuation_ms": 6024,
|
| 121 |
+
"spelling_verdict": "TN",
|
| 122 |
+
"grammar_verdict": "TN",
|
| 123 |
+
"punctuation_verdict": "FP"
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"id": "E005",
|
| 127 |
+
"dataset": "entities",
|
| 128 |
+
"category": "person",
|
| 129 |
+
"input_text": "الدكتور حسن علي أستاذ جامعي",
|
| 130 |
+
"expected": "الدكتور حسن علي أستاذ جامعي",
|
| 131 |
+
"severity": "major",
|
| 132 |
+
"spelling_solo": "الدكتور حسن على أستاذ جامعي",
|
| 133 |
+
"spelling_ms": 3114,
|
| 134 |
+
"grammar_solo": "الدكتور حسن علي أستاذ جامعي",
|
| 135 |
+
"grammar_ms": 3415,
|
| 136 |
+
"punctuation_solo": "الدكتور حسن علي أستاذ جامعي.",
|
| 137 |
+
"punctuation_ms": 3948,
|
| 138 |
+
"spelling_verdict": "FP",
|
| 139 |
+
"grammar_verdict": "TN",
|
| 140 |
+
"punctuation_verdict": "FP"
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"id": "E006",
|
| 144 |
+
"dataset": "entities",
|
| 145 |
+
"category": "person",
|
| 146 |
+
"input_text": "السيدة فاطمة الزهراء معلمة",
|
| 147 |
+
"expected": "السيدة فاطمة الزهراء معلمة",
|
| 148 |
+
"severity": "major",
|
| 149 |
+
"spelling_solo": "السيدة فاطمة الزهراء معلمة",
|
| 150 |
+
"spelling_ms": 5634,
|
| 151 |
+
"grammar_solo": "السيدة فاطمة الزهراء معلمة",
|
| 152 |
+
"grammar_ms": 3984,
|
| 153 |
+
"punctuation_solo": "السيدة فاطمة الزهراء معلمة.",
|
| 154 |
+
"punctuation_ms": 4231,
|
| 155 |
+
"spelling_verdict": "TN",
|
| 156 |
+
"grammar_verdict": "TN",
|
| 157 |
+
"punctuation_verdict": "FP"
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"id": "E007",
|
| 161 |
+
"dataset": "entities",
|
| 162 |
+
"category": "person",
|
| 163 |
+
"input_text": "الأستاذ عمر بن الخطاب عادل",
|
| 164 |
+
"expected": "الأستاذ عمر بن الخطاب عادل",
|
| 165 |
+
"severity": "major",
|
| 166 |
+
"spelling_solo": "الأستاذ عمر بن الخطاب عادل",
|
| 167 |
+
"spelling_ms": 4630,
|
| 168 |
+
"grammar_solo": "الأستاذ عمر بن الخطاب عادل",
|
| 169 |
+
"grammar_ms": 5821,
|
| 170 |
+
"punctuation_solo": "الأستاذ عمر بن الخطاب عادل.",
|
| 171 |
+
"punctuation_ms": 4079,
|
| 172 |
+
"spelling_verdict": "TN",
|
| 173 |
+
"grammar_verdict": "TN",
|
| 174 |
+
"punctuation_verdict": "FP"
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"id": "E008",
|
| 178 |
+
"dataset": "entities",
|
| 179 |
+
"category": "person",
|
| 180 |
+
"input_text": "خالد بن الوليد قائد عظيم",
|
| 181 |
+
"expected": "خالد بن الوليد قائد عظيم",
|
| 182 |
+
"severity": "major",
|
| 183 |
+
"spelling_solo": "خالد بن الوليد قائد عظيم",
|
| 184 |
+
"spelling_ms": 4379,
|
| 185 |
+
"grammar_solo": "خالد بن الوليد قائد عظيم",
|
| 186 |
+
"grammar_ms": 4430,
|
| 187 |
+
"punctuation_solo": "خالد بن الوليد قائد عظيم.",
|
| 188 |
+
"punctuation_ms": 4472,
|
| 189 |
+
"spelling_verdict": "TN",
|
| 190 |
+
"grammar_verdict": "TN",
|
| 191 |
+
"punctuation_verdict": "FP"
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"id": "E009",
|
| 195 |
+
"dataset": "entities",
|
| 196 |
+
"category": "person",
|
| 197 |
+
"input_text": "صلاح الدين الأيوبي حرر القدس",
|
| 198 |
+
"expected": "صلاح الدين الأيوبي حرر القدس",
|
| 199 |
+
"severity": "major",
|
| 200 |
+
"spelling_solo": "صلاح الدين الأيوبي حر القدس",
|
| 201 |
+
"spelling_ms": 4345,
|
| 202 |
+
"grammar_solo": "صلاح الدين الأيوبي حرر القدس",
|
| 203 |
+
"grammar_ms": 4691,
|
| 204 |
+
"punctuation_solo": "صلاح الدين الأيوبي حرر القدس.",
|
| 205 |
+
"punctuation_ms": 4084,
|
| 206 |
+
"spelling_verdict": "FP",
|
| 207 |
+
"grammar_verdict": "TN",
|
| 208 |
+
"punctuation_verdict": "FP"
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"id": "E010",
|
| 212 |
+
"dataset": "entities",
|
| 213 |
+
"category": "person",
|
| 214 |
+
"input_text": "ابن سينا عالم عربي مشهور",
|
| 215 |
+
"expected": "ابن سينا عالم عربي مشهور",
|
| 216 |
+
"severity": "major",
|
| 217 |
+
"spelling_solo": "ابن سينا عالم عربي مشهور",
|
| 218 |
+
"spelling_ms": 5819,
|
| 219 |
+
"grammar_solo": "ابن سينا عالم عربي مشهور",
|
| 220 |
+
"grammar_ms": 6752,
|
| 221 |
+
"punctuation_solo": "ابن سينا عالم عربي مشهور.",
|
| 222 |
+
"punctuation_ms": 3932,
|
| 223 |
+
"spelling_verdict": "TN",
|
| 224 |
+
"grammar_verdict": "TN",
|
| 225 |
+
"punctuation_verdict": "FP"
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"id": "E011",
|
| 229 |
+
"dataset": "entities",
|
| 230 |
+
"category": "place",
|
| 231 |
+
"input_text": "جامعة القاهرة من أعرق الجامعات",
|
| 232 |
+
"expected": "جامعة القاهرة من أعرق الجامعات",
|
| 233 |
+
"severity": "major",
|
| 234 |
+
"spelling_solo": "جامعة القاهرة من أعمق الجامعات",
|
| 235 |
+
"spelling_ms": 3997,
|
| 236 |
+
"grammar_solo": "جامعة القاهرة من أعرق الجامعات",
|
| 237 |
+
"grammar_ms": 5990,
|
| 238 |
+
"punctuation_solo": "جامعة القاهرة من أعرق الجامعات.",
|
| 239 |
+
"punctuation_ms": 4690,
|
| 240 |
+
"spelling_verdict": "FP",
|
| 241 |
+
"grammar_verdict": "TN",
|
| 242 |
+
"punctuation_verdict": "FP"
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"id": "E012",
|
| 246 |
+
"dataset": "entities",
|
| 247 |
+
"category": "place",
|
| 248 |
+
"input_text": "مدينة الرياض عاصمة المملكة",
|
| 249 |
+
"expected": "مدينة الرياض عاصمة المملكة",
|
| 250 |
+
"severity": "major",
|
| 251 |
+
"spelling_solo": "مدينة الرياض عاصمة المملكة",
|
| 252 |
+
"spelling_ms": 3736,
|
| 253 |
+
"grammar_solo": "مدينة الرياض عاصمة المملكة",
|
| 254 |
+
"grammar_ms": 4113,
|
| 255 |
+
"punctuation_solo": "مدينة الرياض عاصمة المملكة.",
|
| 256 |
+
"punctuation_ms": 5125,
|
| 257 |
+
"spelling_verdict": "TN",
|
| 258 |
+
"grammar_verdict": "TN",
|
| 259 |
+
"punctuation_verdict": "FP"
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"id": "E013",
|
| 263 |
+
"dataset": "entities",
|
| 264 |
+
"category": "place",
|
| 265 |
+
"input_text": "دبي مدينة عصرية وجميلة",
|
| 266 |
+
"expected": "دبي مدينة عصرية وجميلة",
|
| 267 |
+
"severity": "major",
|
| 268 |
+
"spelling_solo": "دبي مدينة عصرية وجميلة",
|
| 269 |
+
"spelling_ms": 2608,
|
| 270 |
+
"grammar_solo": "دبي مدينة عصرية وجميلة",
|
| 271 |
+
"grammar_ms": 2415,
|
| 272 |
+
"punctuation_solo": "دبي مدينة عصرية وجميلة.",
|
| 273 |
+
"punctuation_ms": 2801,
|
| 274 |
+
"spelling_verdict": "TN",
|
| 275 |
+
"grammar_verdict": "TN",
|
| 276 |
+
"punctuation_verdict": "FP"
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"id": "E014",
|
| 280 |
+
"dataset": "entities",
|
| 281 |
+
"category": "place",
|
| 282 |
+
"input_text": "القدس مدينة مقدسة عند المسلمين",
|
| 283 |
+
"expected": "القدس مدينة مقدسة عند المسلمين",
|
| 284 |
+
"severity": "major",
|
| 285 |
+
"spelling_solo": "القدس مدينة مقدسة عند المسلمين",
|
| 286 |
+
"spelling_ms": 2896,
|
| 287 |
+
"grammar_solo": "القدس مدينة مقدسة عند المسلمين",
|
| 288 |
+
"grammar_ms": 2412,
|
| 289 |
+
"punctuation_solo": "القدس مدينة مقدسة عند المسلمين.",
|
| 290 |
+
"punctuation_ms": 2199,
|
| 291 |
+
"spelling_verdict": "TN",
|
| 292 |
+
"grammar_verdict": "TN",
|
| 293 |
+
"punctuation_verdict": "FP"
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"id": "E015",
|
| 297 |
+
"dataset": "entities",
|
| 298 |
+
"category": "place",
|
| 299 |
+
"input_text": "مكة المكرمة أطهر البقاع",
|
| 300 |
+
"expected": "مكة المكرمة أطهر البقاع",
|
| 301 |
+
"severity": "major",
|
| 302 |
+
"spelling_solo": "مكة المكرمة أطهر البقاع",
|
| 303 |
+
"spelling_ms": 2397,
|
| 304 |
+
"grammar_solo": "مكة المكرمة أطهر البقاع",
|
| 305 |
+
"grammar_ms": 2233,
|
| 306 |
+
"punctuation_solo": "مكة المكرمة أطهر البقاع.",
|
| 307 |
+
"punctuation_ms": 2567,
|
| 308 |
+
"spelling_verdict": "TN",
|
| 309 |
+
"grammar_verdict": "TN",
|
| 310 |
+
"punctuation_verdict": "FP"
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"id": "E016",
|
| 314 |
+
"dataset": "entities",
|
| 315 |
+
"category": "place",
|
| 316 |
+
"input_text": "المدينة المنورة طابة الطيبة",
|
| 317 |
+
"expected": "المدينة المنورة طابة الطيبة",
|
| 318 |
+
"severity": "major",
|
| 319 |
+
"spelling_solo": "المدينة المنورة الطيبة",
|
| 320 |
+
"spelling_ms": 1998,
|
| 321 |
+
"grammar_solo": "المدينة المنورة طابة طيبة",
|
| 322 |
+
"grammar_ms": 2088,
|
| 323 |
+
"punctuation_solo": "المدينة المنورة طابة الطيبة.",
|
| 324 |
+
"punctuation_ms": 2206,
|
| 325 |
+
"spelling_verdict": "FP",
|
| 326 |
+
"grammar_verdict": "FP",
|
| 327 |
+
"punctuation_verdict": "FP"
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"id": "E017",
|
| 331 |
+
"dataset": "entities",
|
| 332 |
+
"category": "place",
|
| 333 |
+
"input_text": "بغداد عاصمة العراق",
|
| 334 |
+
"expected": "بغداد عاصمة العراق",
|
| 335 |
+
"severity": "major",
|
| 336 |
+
"spelling_solo": "بغداد عاصمة العراق",
|
| 337 |
+
"spelling_ms": 2113,
|
| 338 |
+
"grammar_solo": "بغداد عاصمة العراق",
|
| 339 |
+
"grammar_ms": 1857,
|
| 340 |
+
"punctuation_solo": "بغداد عاصمة العراق.",
|
| 341 |
+
"punctuation_ms": 2138,
|
| 342 |
+
"spelling_verdict": "TN",
|
| 343 |
+
"grammar_verdict": "TN",
|
| 344 |
+
"punctuation_verdict": "FP"
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"id": "E018",
|
| 348 |
+
"dataset": "entities",
|
| 349 |
+
"category": "place",
|
| 350 |
+
"input_text": "دمشق أقدم عاصمة في التاريخ",
|
| 351 |
+
"expected": "دمشق أقدم عاصمة في التاريخ",
|
| 352 |
+
"severity": "major",
|
| 353 |
+
"spelling_solo": "دمشق أقدم عاصمة في التاريخ",
|
| 354 |
+
"spelling_ms": 2281,
|
| 355 |
+
"grammar_solo": "دمشق أقدم عاصمة في التاريخ",
|
| 356 |
+
"grammar_ms": 2329,
|
| 357 |
+
"punctuation_solo": "دمشق أقدم عاصمة في التاريخ.",
|
| 358 |
+
"punctuation_ms": 2478,
|
| 359 |
+
"spelling_verdict": "TN",
|
| 360 |
+
"grammar_verdict": "TN",
|
| 361 |
+
"punctuation_verdict": "FP"
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"id": "E019",
|
| 365 |
+
"dataset": "entities",
|
| 366 |
+
"category": "company",
|
| 367 |
+
"input_text": "شركة OpenAI تطور الذكاء الاصطناعي",
|
| 368 |
+
"expected": "شركة OpenAI تطور الذكاء الاصطناعي",
|
| 369 |
+
"severity": "major",
|
| 370 |
+
"spelling_solo": "شركة OpenAI تطور الذكاء الاصطناعي",
|
| 371 |
+
"spelling_ms": 7894,
|
| 372 |
+
"grammar_solo": "شركة OpenAI تطور الذكاء الاصطناعي",
|
| 373 |
+
"grammar_ms": 2409,
|
| 374 |
+
"punctuation_solo": "شركة OpenAI تطور الذكاء الاصطناعي",
|
| 375 |
+
"punctuation_ms": 2268,
|
| 376 |
+
"spelling_verdict": "TN",
|
| 377 |
+
"grammar_verdict": "TN",
|
| 378 |
+
"punctuation_verdict": "TN"
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"id": "E020",
|
| 382 |
+
"dataset": "entities",
|
| 383 |
+
"category": "company",
|
| 384 |
+
"input_text": "شركة Google عملاق التقنية",
|
| 385 |
+
"expected": "شركة Google عملاق التقنية",
|
| 386 |
+
"severity": "major",
|
| 387 |
+
"spelling_solo": "شركة جوجل جوجل عملاق التقنية",
|
| 388 |
+
"spelling_ms": 5865,
|
| 389 |
+
"grammar_solo": "شركة Google عملاق التقنية",
|
| 390 |
+
"grammar_ms": 2176,
|
| 391 |
+
"punctuation_solo": "شركة Google عملاق التقنية.",
|
| 392 |
+
"punctuation_ms": 2034,
|
| 393 |
+
"spelling_verdict": "FP",
|
| 394 |
+
"grammar_verdict": "TN",
|
| 395 |
+
"punctuation_verdict": "FP"
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"id": "E021",
|
| 399 |
+
"dataset": "entities",
|
| 400 |
+
"category": "company",
|
| 401 |
+
"input_text": "شركة Microsoft تنتج البرمجيات",
|
| 402 |
+
"expected": "شركة Microsoft تنتج البرمجيات",
|
| 403 |
+
"severity": "major",
|
| 404 |
+
"spelling_solo": "شركة مايكروسوفت تنتج البرمجيات",
|
| 405 |
+
"spelling_ms": 4482,
|
| 406 |
+
"grammar_solo": "شركة Microsoft تنتج البرمجيات",
|
| 407 |
+
"grammar_ms": 2363,
|
| 408 |
+
"punctuation_solo": "شركة Microsoft تنتج البرمجيات.",
|
| 409 |
+
"punctuation_ms": 2847,
|
| 410 |
+
"spelling_verdict": "FP",
|
| 411 |
+
"grammar_verdict": "TN",
|
| 412 |
+
"punctuation_verdict": "FP"
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"id": "E022",
|
| 416 |
+
"dataset": "entities",
|
| 417 |
+
"category": "company",
|
| 418 |
+
"input_text": "منصة GitHub للمطورين",
|
| 419 |
+
"expected": "منصة GitHub للمطورين",
|
| 420 |
+
"severity": "major",
|
| 421 |
+
"spelling_solo": "منصة GitHub المطورين",
|
| 422 |
+
"spelling_ms": 6268,
|
| 423 |
+
"grammar_solo": "منصة GitHuب للمطورين",
|
| 424 |
+
"grammar_ms": 2435,
|
| 425 |
+
"punctuation_solo": "منصة GitHub للمطورين.",
|
| 426 |
+
"punctuation_ms": 2379,
|
| 427 |
+
"spelling_verdict": "FP",
|
| 428 |
+
"grammar_verdict": "FP",
|
| 429 |
+
"punctuation_verdict": "FP"
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"id": "E023",
|
| 433 |
+
"dataset": "entities",
|
| 434 |
+
"category": "company",
|
| 435 |
+
"input_text": "شركة Tesla للسيارات الكهربائية",
|
| 436 |
+
"expected": "شركة Tesla للسيارات الكهربائية",
|
| 437 |
+
"severity": "major",
|
| 438 |
+
"spelling_solo": "شركة تي اس لا للسيارات الكهربائية",
|
| 439 |
+
"spelling_ms": 6245,
|
| 440 |
+
"grammar_solo": "شركة Teسla للسيارات الكهربائية",
|
| 441 |
+
"grammar_ms": 2639,
|
| 442 |
+
"punctuation_solo": "شركة Tesla للسيارات الكهربائية.",
|
| 443 |
+
"punctuation_ms": 2648,
|
| 444 |
+
"spelling_verdict": "FP",
|
| 445 |
+
"grammar_verdict": "FP",
|
| 446 |
+
"punctuation_verdict": "FP"
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"id": "E024",
|
| 450 |
+
"dataset": "entities",
|
| 451 |
+
"category": "tech",
|
| 452 |
+
"input_text": "أستخدم Python في البرمجة",
|
| 453 |
+
"expected": "أستخدم Python في البرمجة",
|
| 454 |
+
"severity": "major",
|
| 455 |
+
"spelling_solo": "أستخدم Python في البرمجة",
|
| 456 |
+
"spelling_ms": 6228,
|
| 457 |
+
"grammar_solo": "أستخدمت Python في البرمجة",
|
| 458 |
+
"grammar_ms": 2287,
|
| 459 |
+
"punctuation_solo": "أستخدم Python في البرمجة؟",
|
| 460 |
+
"punctuation_ms": 2277,
|
| 461 |
+
"spelling_verdict": "TN",
|
| 462 |
+
"grammar_verdict": "FP",
|
| 463 |
+
"punctuation_verdict": "FP"
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"id": "E025",
|
| 467 |
+
"dataset": "entities",
|
| 468 |
+
"category": "tech",
|
| 469 |
+
"input_text": "إطار TensorFlow مفيد للتعلم",
|
| 470 |
+
"expected": "إطار TensorFlow مفيد للتعلم",
|
| 471 |
+
"severity": "major",
|
| 472 |
+
"spelling_solo": "إطار TensorFlow مفيد للتعلم",
|
| 473 |
+
"spelling_ms": 6426,
|
| 474 |
+
"grammar_solo": "إطار TensorFlow مفيد للتعلم",
|
| 475 |
+
"grammar_ms": 2480,
|
| 476 |
+
"punctuation_solo": "إطار TensorFlow، مفيد: للتعلم",
|
| 477 |
+
"punctuation_ms": 2703,
|
| 478 |
+
"spelling_verdict": "TN",
|
| 479 |
+
"grammar_verdict": "TN",
|
| 480 |
+
"punctuation_verdict": "FP"
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"id": "E026",
|
| 484 |
+
"dataset": "entities",
|
| 485 |
+
"category": "tech",
|
| 486 |
+
"input_text": "مكتبة PyTorch للتعلم العميق",
|
| 487 |
+
"expected": "مكتبة PyTorch للتعلم العميق",
|
| 488 |
+
"severity": "major",
|
| 489 |
+
"spelling_solo": "مكتبة PyTorch للتعلم العميق",
|
| 490 |
+
"spelling_ms": 5846,
|
| 491 |
+
"grammar_solo": "مكتبة PyTorch للتعلم العميق",
|
| 492 |
+
"grammar_ms": 2369,
|
| 493 |
+
"punctuation_solo": "مكتبة PyTorch للتعلم العميق.",
|
| 494 |
+
"punctuation_ms": 2808,
|
| 495 |
+
"spelling_verdict": "TN",
|
| 496 |
+
"grammar_verdict": "TN",
|
| 497 |
+
"punctuation_verdict": "FP"
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"id": "E027",
|
| 501 |
+
"dataset": "entities",
|
| 502 |
+
"category": "tech",
|
| 503 |
+
"input_text": "منصة Node.js للخوادم",
|
| 504 |
+
"expected": "منصة Node.js للخوادم",
|
| 505 |
+
"severity": "major",
|
| 506 |
+
"spelling_solo": "منصة Node. js للخوادم",
|
| 507 |
+
"spelling_ms": 5623,
|
| 508 |
+
"grammar_solo": "منصة Node ، jة للخوادم",
|
| 509 |
+
"grammar_ms": 2873,
|
| 510 |
+
"punctuation_solo": "منصة Node. js للخوادم:",
|
| 511 |
+
"punctuation_ms": 824,
|
| 512 |
+
"spelling_verdict": "FP",
|
| 513 |
+
"grammar_verdict": "FP",
|
| 514 |
+
"punctuation_verdict": "FP"
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"id": "E028",
|
| 518 |
+
"dataset": "entities",
|
| 519 |
+
"category": "tech",
|
| 520 |
+
"input_text": "لغة JavaScript للويب",
|
| 521 |
+
"expected": "لغة JavaScript للويب",
|
| 522 |
+
"severity": "major",
|
| 523 |
+
"spelling_solo": "لغة JavaScript الويب",
|
| 524 |
+
"spelling_ms": 4824,
|
| 525 |
+
"grammar_solo": "لغة JavaScript للويب",
|
| 526 |
+
"grammar_ms": 800,
|
| 527 |
+
"punctuation_solo": "لغة JavaScript: للويب",
|
| 528 |
+
"punctuation_ms": 896,
|
| 529 |
+
"spelling_verdict": "FP",
|
| 530 |
+
"grammar_verdict": "TN",
|
| 531 |
+
"punctuation_verdict": "FP"
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"id": "E029",
|
| 535 |
+
"dataset": "entities",
|
| 536 |
+
"category": "tech",
|
| 537 |
+
"input_text": "قاعدة بيانات MongoDB جيدة",
|
| 538 |
+
"expected": "قاعدة بيانات MongoDB جيدة",
|
| 539 |
+
"severity": "major",
|
| 540 |
+
"spelling_solo": "قاعدة بيانات MongoDB جيدة",
|
| 541 |
+
"spelling_ms": 4214,
|
| 542 |
+
"grammar_solo": "قاعدة بيانات MongoDB جيدة",
|
| 543 |
+
"grammar_ms": 935,
|
| 544 |
+
"punctuation_solo": "قاعدة بيانات MongoDB. جيدة",
|
| 545 |
+
"punctuation_ms": 801,
|
| 546 |
+
"spelling_verdict": "TN",
|
| 547 |
+
"grammar_verdict": "TN",
|
| 548 |
+
"punctuation_verdict": "FP"
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"id": "E030",
|
| 552 |
+
"dataset": "entities",
|
| 553 |
+
"category": "tech",
|
| 554 |
+
"input_text": "خدمة Docker للحاويات",
|
| 555 |
+
"expected": "خدمة Docker للحاويات",
|
| 556 |
+
"severity": "major",
|
| 557 |
+
"spelling_solo": "خدمة Docker للحاويات",
|
| 558 |
+
"spelling_ms": 3841,
|
| 559 |
+
"grammar_solo": "خدمة Docker للحاويات",
|
| 560 |
+
"grammar_ms": 941,
|
| 561 |
+
"punctuation_solo": "خدمة Docker للحاويات.",
|
| 562 |
+
"punctuation_ms": 732,
|
| 563 |
+
"spelling_verdict": "TN",
|
| 564 |
+
"grammar_verdict": "TN",
|
| 565 |
+
"punctuation_verdict": "FP"
|
| 566 |
+
}
|
| 567 |
+
]
|
| 568 |
+
}
|
tests/v2/reports/level3_integrated_results.json
ADDED
|
@@ -0,0 +1,1306 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"timestamp": "2026-06-23T18:54:52Z",
|
| 3 |
+
"target": "https://bayan10-bayan-api.hf.space",
|
| 4 |
+
"analysis": {
|
| 5 |
+
"total": 80,
|
| 6 |
+
"aggregate": {
|
| 7 |
+
"TP": 22,
|
| 8 |
+
"TN": 0,
|
| 9 |
+
"FP": 58,
|
| 10 |
+
"FN": 0,
|
| 11 |
+
"pass_rate": 0.275
|
| 12 |
+
},
|
| 13 |
+
"by_dataset": {
|
| 14 |
+
"spelling": {
|
| 15 |
+
"TP": 22,
|
| 16 |
+
"TN": 0,
|
| 17 |
+
"FP": 58,
|
| 18 |
+
"FN": 0,
|
| 19 |
+
"total": 80,
|
| 20 |
+
"pass_rate": 0.275
|
| 21 |
+
}
|
| 22 |
+
}
|
| 23 |
+
},
|
| 24 |
+
"results": [
|
| 25 |
+
{
|
| 26 |
+
"id": "S001",
|
| 27 |
+
"dataset": "spelling",
|
| 28 |
+
"category": "hamza",
|
| 29 |
+
"input_text": "انا طالب في الجامعة",
|
| 30 |
+
"expected": "أنا طالب في الجامعة",
|
| 31 |
+
"severity": "major",
|
| 32 |
+
"pipeline_corrected": "أنا طالب في الجامعة.",
|
| 33 |
+
"pipeline_suggestions": 2,
|
| 34 |
+
"pipeline_ms": 8033,
|
| 35 |
+
"spelling_ms": 3645,
|
| 36 |
+
"grammar_ms": 670,
|
| 37 |
+
"punctuation_ms": 2748,
|
| 38 |
+
"verdict": "FP",
|
| 39 |
+
"detail": "Wrong correction"
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"id": "S002",
|
| 43 |
+
"dataset": "spelling",
|
| 44 |
+
"category": "hamza",
|
| 45 |
+
"input_text": "اذا جاء الربيع تزهر الأشجار",
|
| 46 |
+
"expected": "إذا جاء الربيع تزهر الأشجار",
|
| 47 |
+
"severity": "major",
|
| 48 |
+
"pipeline_corrected": "إذا جاء الربيع تزهر الأشجار.",
|
| 49 |
+
"pipeline_suggestions": 2,
|
| 50 |
+
"pipeline_ms": 5444,
|
| 51 |
+
"spelling_ms": 3501,
|
| 52 |
+
"grammar_ms": 586,
|
| 53 |
+
"punctuation_ms": 522,
|
| 54 |
+
"verdict": "FP",
|
| 55 |
+
"detail": "Wrong correction"
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"id": "S003",
|
| 59 |
+
"dataset": "spelling",
|
| 60 |
+
"category": "hamza",
|
| 61 |
+
"input_text": "ايضا هذا الأمر مهم جداً",
|
| 62 |
+
"expected": "أيضاً هذا الأمر مهم جداً",
|
| 63 |
+
"severity": "major",
|
| 64 |
+
"pipeline_corrected": "ايضا هذا الأمر مهم جداً.",
|
| 65 |
+
"pipeline_suggestions": 1,
|
| 66 |
+
"pipeline_ms": 5593,
|
| 67 |
+
"spelling_ms": 3361,
|
| 68 |
+
"grammar_ms": 654,
|
| 69 |
+
"punctuation_ms": 664,
|
| 70 |
+
"verdict": "FP",
|
| 71 |
+
"detail": "Wrong correction"
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"id": "S004",
|
| 75 |
+
"dataset": "spelling",
|
| 76 |
+
"category": "hamza",
|
| 77 |
+
"input_text": "لان الأمر يتعلق بالمستقبل",
|
| 78 |
+
"expected": "لأن الأمر يتعلق بالمستقبل",
|
| 79 |
+
"severity": "major",
|
| 80 |
+
"pipeline_corrected": "لأن الأمر يتعلق بالمستقبل.",
|
| 81 |
+
"pipeline_suggestions": 2,
|
| 82 |
+
"pipeline_ms": 5150,
|
| 83 |
+
"spelling_ms": 3364,
|
| 84 |
+
"grammar_ms": 494,
|
| 85 |
+
"punctuation_ms": 569,
|
| 86 |
+
"verdict": "FP",
|
| 87 |
+
"detail": "Wrong correction"
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"id": "S005",
|
| 91 |
+
"dataset": "spelling",
|
| 92 |
+
"category": "hamza",
|
| 93 |
+
"input_text": "اين ذهبت أمس",
|
| 94 |
+
"expected": "أين ذهبت أمس",
|
| 95 |
+
"severity": "major",
|
| 96 |
+
"pipeline_corrected": "أين ذهبت أمس؟",
|
| 97 |
+
"pipeline_suggestions": 2,
|
| 98 |
+
"pipeline_ms": 3457,
|
| 99 |
+
"spelling_ms": 1889,
|
| 100 |
+
"grammar_ms": 436,
|
| 101 |
+
"punctuation_ms": 338,
|
| 102 |
+
"verdict": "FP",
|
| 103 |
+
"detail": "Wrong correction"
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"id": "S006",
|
| 107 |
+
"dataset": "spelling",
|
| 108 |
+
"category": "hamza",
|
| 109 |
+
"input_text": "اول مرة أزور هذا المكان",
|
| 110 |
+
"expected": "أول مرة أزور هذا المكان",
|
| 111 |
+
"severity": "major",
|
| 112 |
+
"pipeline_corrected": "اول مرة أزور هذا المكان.",
|
| 113 |
+
"pipeline_suggestions": 1,
|
| 114 |
+
"pipeline_ms": 5318,
|
| 115 |
+
"spelling_ms": 3370,
|
| 116 |
+
"grammar_ms": 655,
|
| 117 |
+
"punctuation_ms": 558,
|
| 118 |
+
"verdict": "FP",
|
| 119 |
+
"detail": "Wrong correction"
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"id": "S007",
|
| 123 |
+
"dataset": "spelling",
|
| 124 |
+
"category": "hamza",
|
| 125 |
+
"input_text": "هذا او ذاك لا فرق",
|
| 126 |
+
"expected": "هذا أو ذاك لا فرق",
|
| 127 |
+
"severity": "major",
|
| 128 |
+
"pipeline_corrected": "هذا أو ذاك لا فرق.",
|
| 129 |
+
"pipeline_suggestions": 2,
|
| 130 |
+
"pipeline_ms": 6027,
|
| 131 |
+
"spelling_ms": 4153,
|
| 132 |
+
"grammar_ms": 604,
|
| 133 |
+
"punctuation_ms": 701,
|
| 134 |
+
"verdict": "FP",
|
| 135 |
+
"detail": "Wrong correction"
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"id": "S008",
|
| 139 |
+
"dataset": "spelling",
|
| 140 |
+
"category": "hamza",
|
| 141 |
+
"input_text": "اكبر مدينة في العالم",
|
| 142 |
+
"expected": "أكبر مدينة في العالم",
|
| 143 |
+
"severity": "major",
|
| 144 |
+
"pipeline_corrected": "أكبر مدينة في العالم؟",
|
| 145 |
+
"pipeline_suggestions": 2,
|
| 146 |
+
"pipeline_ms": 8374,
|
| 147 |
+
"spelling_ms": 4040,
|
| 148 |
+
"grammar_ms": 610,
|
| 149 |
+
"punctuation_ms": 2543,
|
| 150 |
+
"verdict": "FP",
|
| 151 |
+
"detail": "Wrong correction"
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"id": "S009",
|
| 155 |
+
"dataset": "spelling",
|
| 156 |
+
"category": "hamza",
|
| 157 |
+
"input_text": "اصغر طالب في الصف",
|
| 158 |
+
"expected": "أصغر طالب في الصف",
|
| 159 |
+
"severity": "major",
|
| 160 |
+
"pipeline_corrected": "أصغر طالب في الصف؟",
|
| 161 |
+
"pipeline_suggestions": 2,
|
| 162 |
+
"pipeline_ms": 4214,
|
| 163 |
+
"spelling_ms": 2207,
|
| 164 |
+
"grammar_ms": 595,
|
| 165 |
+
"punctuation_ms": 513,
|
| 166 |
+
"verdict": "FP",
|
| 167 |
+
"detail": "Wrong correction"
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"id": "S010",
|
| 171 |
+
"dataset": "spelling",
|
| 172 |
+
"category": "hamza",
|
| 173 |
+
"input_text": "ابناء الوطن يعملون بجد",
|
| 174 |
+
"expected": "أبناء الوطن يعملون بجد",
|
| 175 |
+
"severity": "major",
|
| 176 |
+
"pipeline_corrected": "أبناء الوطن يعملون بجد.",
|
| 177 |
+
"pipeline_suggestions": 2,
|
| 178 |
+
"pipeline_ms": 4294,
|
| 179 |
+
"spelling_ms": 2184,
|
| 180 |
+
"grammar_ms": 699,
|
| 181 |
+
"punctuation_ms": 620,
|
| 182 |
+
"verdict": "FP",
|
| 183 |
+
"detail": "Wrong correction"
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"id": "S011",
|
| 187 |
+
"dataset": "spelling",
|
| 188 |
+
"category": "hamza",
|
| 189 |
+
"input_text": "اطفال المدرسة يلعبون",
|
| 190 |
+
"expected": "أطفال المدرسة يلعبون",
|
| 191 |
+
"severity": "major",
|
| 192 |
+
"pipeline_corrected": "أطفال المدرسة يلعبون.",
|
| 193 |
+
"pipeline_suggestions": 2,
|
| 194 |
+
"pipeline_ms": 4345,
|
| 195 |
+
"spelling_ms": 2268,
|
| 196 |
+
"grammar_ms": 542,
|
| 197 |
+
"punctuation_ms": 567,
|
| 198 |
+
"verdict": "FP",
|
| 199 |
+
"detail": "Wrong correction"
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"id": "S012",
|
| 203 |
+
"dataset": "spelling",
|
| 204 |
+
"category": "hamza",
|
| 205 |
+
"input_text": "اخيراً وصلنا إلى الهدف",
|
| 206 |
+
"expected": "أخيراً وصلنا إلى الهدف",
|
| 207 |
+
"severity": "major",
|
| 208 |
+
"pipeline_corrected": "أخيراً وصلنا إلى الهدف.",
|
| 209 |
+
"pipeline_suggestions": 2,
|
| 210 |
+
"pipeline_ms": 6255,
|
| 211 |
+
"spelling_ms": 4085,
|
| 212 |
+
"grammar_ms": 596,
|
| 213 |
+
"punctuation_ms": 729,
|
| 214 |
+
"verdict": "FP",
|
| 215 |
+
"detail": "Wrong correction"
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"id": "S013",
|
| 219 |
+
"dataset": "spelling",
|
| 220 |
+
"category": "hamza",
|
| 221 |
+
"input_text": "وقف امام المدرسة",
|
| 222 |
+
"expected": "وقف أمام المدرسة",
|
| 223 |
+
"severity": "major",
|
| 224 |
+
"pipeline_corrected": "وقف أمام المدرسة.",
|
| 225 |
+
"pipeline_suggestions": 2,
|
| 226 |
+
"pipeline_ms": 2917,
|
| 227 |
+
"spelling_ms": 1380,
|
| 228 |
+
"grammar_ms": 441,
|
| 229 |
+
"punctuation_ms": 481,
|
| 230 |
+
"verdict": "FP",
|
| 231 |
+
"detail": "Wrong correction"
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"id": "S014",
|
| 235 |
+
"dataset": "spelling",
|
| 236 |
+
"category": "hamza",
|
| 237 |
+
"input_text": "انت طالب مجتهد",
|
| 238 |
+
"expected": "أنت طالب مجتهد",
|
| 239 |
+
"severity": "major",
|
| 240 |
+
"pipeline_corrected": "أنت طالب مجتهد.",
|
| 241 |
+
"pipeline_suggestions": 2,
|
| 242 |
+
"pipeline_ms": 3440,
|
| 243 |
+
"spelling_ms": 1755,
|
| 244 |
+
"grammar_ms": 535,
|
| 245 |
+
"punctuation_ms": 337,
|
| 246 |
+
"verdict": "FP",
|
| 247 |
+
"detail": "Wrong correction"
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"id": "S015",
|
| 251 |
+
"dataset": "spelling",
|
| 252 |
+
"category": "hamza",
|
| 253 |
+
"input_text": "اننا نحب الوطن",
|
| 254 |
+
"expected": "إننا نحب الوطن",
|
| 255 |
+
"severity": "major",
|
| 256 |
+
"pipeline_corrected": "اننا نحب الوطن.",
|
| 257 |
+
"pipeline_suggestions": 1,
|
| 258 |
+
"pipeline_ms": 4129,
|
| 259 |
+
"spelling_ms": 2441,
|
| 260 |
+
"grammar_ms": 440,
|
| 261 |
+
"punctuation_ms": 463,
|
| 262 |
+
"verdict": "FP",
|
| 263 |
+
"detail": "Wrong correction"
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"id": "S016",
|
| 267 |
+
"dataset": "spelling",
|
| 268 |
+
"category": "hamza",
|
| 269 |
+
"input_text": "ان شاء الله سنفوز",
|
| 270 |
+
"expected": "إن شاء الله سنفوز",
|
| 271 |
+
"severity": "major",
|
| 272 |
+
"pipeline_corrected": "إن شاء الله سنفوز.",
|
| 273 |
+
"pipeline_suggestions": 2,
|
| 274 |
+
"pipeline_ms": 5342,
|
| 275 |
+
"spelling_ms": 3569,
|
| 276 |
+
"grammar_ms": 636,
|
| 277 |
+
"punctuation_ms": 533,
|
| 278 |
+
"verdict": "FP",
|
| 279 |
+
"detail": "Wrong correction"
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"id": "S017",
|
| 283 |
+
"dataset": "spelling",
|
| 284 |
+
"category": "hamza",
|
| 285 |
+
"input_text": "اقترب الموعد النهائي",
|
| 286 |
+
"expected": "اقترب الموعد النهائي",
|
| 287 |
+
"severity": "none",
|
| 288 |
+
"pipeline_corrected": "اقترب الموعد النهائي.",
|
| 289 |
+
"pipeline_suggestions": 1,
|
| 290 |
+
"pipeline_ms": 4093,
|
| 291 |
+
"spelling_ms": 1957,
|
| 292 |
+
"grammar_ms": 754,
|
| 293 |
+
"punctuation_ms": 584,
|
| 294 |
+
"verdict": "FP",
|
| 295 |
+
"detail": "Modified correct text"
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"id": "S018",
|
| 299 |
+
"dataset": "spelling",
|
| 300 |
+
"category": "hamza",
|
| 301 |
+
"input_text": "ارسل الرسالة فوراً",
|
| 302 |
+
"expected": "أرسل الرسالة فوراً",
|
| 303 |
+
"severity": "major",
|
| 304 |
+
"pipeline_corrected": "أرسل الرسالة فوراً.",
|
| 305 |
+
"pipeline_suggestions": 2,
|
| 306 |
+
"pipeline_ms": 4064,
|
| 307 |
+
"spelling_ms": 2103,
|
| 308 |
+
"grammar_ms": 651,
|
| 309 |
+
"punctuation_ms": 518,
|
| 310 |
+
"verdict": "FP",
|
| 311 |
+
"detail": "Wrong correction"
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"id": "S019",
|
| 315 |
+
"dataset": "spelling",
|
| 316 |
+
"category": "hamza",
|
| 317 |
+
"input_text": "اخر الأخبار في المساء",
|
| 318 |
+
"expected": "آخر الأخبار في المساء",
|
| 319 |
+
"severity": "major",
|
| 320 |
+
"pipeline_corrected": "آخر الأخبار في المساء.",
|
| 321 |
+
"pipeline_suggestions": 2,
|
| 322 |
+
"pipeline_ms": 4463,
|
| 323 |
+
"spelling_ms": 2236,
|
| 324 |
+
"grammar_ms": 549,
|
| 325 |
+
"punctuation_ms": 721,
|
| 326 |
+
"verdict": "FP",
|
| 327 |
+
"detail": "Wrong correction"
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"id": "S020",
|
| 331 |
+
"dataset": "spelling",
|
| 332 |
+
"category": "hamza",
|
| 333 |
+
"input_text": "اسرع في المشي قليلاً",
|
| 334 |
+
"expected": "أسرع في المشي قليلاً",
|
| 335 |
+
"severity": "major",
|
| 336 |
+
"pipeline_corrected": "أسرع في المشي قليلاً!",
|
| 337 |
+
"pipeline_suggestions": 2,
|
| 338 |
+
"pipeline_ms": 6099,
|
| 339 |
+
"spelling_ms": 3801,
|
| 340 |
+
"grammar_ms": 705,
|
| 341 |
+
"punctuation_ms": 588,
|
| 342 |
+
"verdict": "FP",
|
| 343 |
+
"detail": "Wrong correction"
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"id": "S021",
|
| 347 |
+
"dataset": "spelling",
|
| 348 |
+
"category": "hamza",
|
| 349 |
+
"input_text": "اجمل مكان في العالم",
|
| 350 |
+
"expected": "أجمل مكان في العالم",
|
| 351 |
+
"severity": "major",
|
| 352 |
+
"pipeline_corrected": "أجمل مكان في العالم؟",
|
| 353 |
+
"pipeline_suggestions": 2,
|
| 354 |
+
"pipeline_ms": 4010,
|
| 355 |
+
"spelling_ms": 2218,
|
| 356 |
+
"grammar_ms": 540,
|
| 357 |
+
"punctuation_ms": 408,
|
| 358 |
+
"verdict": "FP",
|
| 359 |
+
"detail": "Wrong correction"
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"id": "S022",
|
| 363 |
+
"dataset": "spelling",
|
| 364 |
+
"category": "hamza",
|
| 365 |
+
"input_text": "اعلن الرئيس عن القرار",
|
| 366 |
+
"expected": "أعلن الرئيس عن القرار",
|
| 367 |
+
"severity": "major",
|
| 368 |
+
"pipeline_corrected": "اعلن الرئيس عن القرار.",
|
| 369 |
+
"pipeline_suggestions": 1,
|
| 370 |
+
"pipeline_ms": 4267,
|
| 371 |
+
"spelling_ms": 2265,
|
| 372 |
+
"grammar_ms": 497,
|
| 373 |
+
"punctuation_ms": 598,
|
| 374 |
+
"verdict": "FP",
|
| 375 |
+
"detail": "Wrong correction"
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"id": "S023",
|
| 379 |
+
"dataset": "spelling",
|
| 380 |
+
"category": "hamza",
|
| 381 |
+
"input_text": "اكد الوزير على الخطة",
|
| 382 |
+
"expected": "أكد الوزير على الخطة",
|
| 383 |
+
"severity": "major",
|
| 384 |
+
"pipeline_corrected": "أكد الوزير على الخطة.",
|
| 385 |
+
"pipeline_suggestions": 2,
|
| 386 |
+
"pipeline_ms": 4566,
|
| 387 |
+
"spelling_ms": 2472,
|
| 388 |
+
"grammar_ms": 554,
|
| 389 |
+
"punctuation_ms": 519,
|
| 390 |
+
"verdict": "FP",
|
| 391 |
+
"detail": "Wrong correction"
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"id": "S024",
|
| 395 |
+
"dataset": "spelling",
|
| 396 |
+
"category": "hamza",
|
| 397 |
+
"input_text": "اشار التقرير إلى ذلك",
|
| 398 |
+
"expected": "أشار التقرير إلى ذلك",
|
| 399 |
+
"severity": "major",
|
| 400 |
+
"pipeline_corrected": "أشار التقرير إلى ذلك.",
|
| 401 |
+
"pipeline_suggestions": 2,
|
| 402 |
+
"pipeline_ms": 4563,
|
| 403 |
+
"spelling_ms": 2521,
|
| 404 |
+
"grammar_ms": 590,
|
| 405 |
+
"punctuation_ms": 568,
|
| 406 |
+
"verdict": "FP",
|
| 407 |
+
"detail": "Wrong correction"
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"id": "S025",
|
| 411 |
+
"dataset": "spelling",
|
| 412 |
+
"category": "hamza",
|
| 413 |
+
"input_text": "اعتقد انه سيحضر غداً",
|
| 414 |
+
"expected": "أعتقد أنه سيحضر غداً",
|
| 415 |
+
"severity": "major",
|
| 416 |
+
"pipeline_corrected": "أعتقد انه سيحضر غداً.",
|
| 417 |
+
"pipeline_suggestions": 2,
|
| 418 |
+
"pipeline_ms": 4144,
|
| 419 |
+
"spelling_ms": 2119,
|
| 420 |
+
"grammar_ms": 652,
|
| 421 |
+
"punctuation_ms": 578,
|
| 422 |
+
"verdict": "FP",
|
| 423 |
+
"detail": "Wrong correction"
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"id": "S026",
|
| 427 |
+
"dataset": "spelling",
|
| 428 |
+
"category": "hamza_prefix",
|
| 429 |
+
"input_text": "والاسعار مرتفعة جداً",
|
| 430 |
+
"expected": "والأسعار مرتفعة جداً",
|
| 431 |
+
"severity": "major",
|
| 432 |
+
"pipeline_corrected": "والأسعار مرتفعة جداً.",
|
| 433 |
+
"pipeline_suggestions": 2,
|
| 434 |
+
"pipeline_ms": 4880,
|
| 435 |
+
"spelling_ms": 2705,
|
| 436 |
+
"grammar_ms": 593,
|
| 437 |
+
"punctuation_ms": 585,
|
| 438 |
+
"verdict": "FP",
|
| 439 |
+
"detail": "Wrong correction"
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"id": "S027",
|
| 443 |
+
"dataset": "spelling",
|
| 444 |
+
"category": "hamza_prefix",
|
| 445 |
+
"input_text": "بالاضافة إلى ذلك",
|
| 446 |
+
"expected": "بالإضافة إلى ذلك",
|
| 447 |
+
"severity": "major",
|
| 448 |
+
"pipeline_corrected": "بالإضافة إلى ذلك.",
|
| 449 |
+
"pipeline_suggestions": 2,
|
| 450 |
+
"pipeline_ms": 4101,
|
| 451 |
+
"spelling_ms": 2414,
|
| 452 |
+
"grammar_ms": 438,
|
| 453 |
+
"punctuation_ms": 442,
|
| 454 |
+
"verdict": "FP",
|
| 455 |
+
"detail": "Wrong correction"
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"id": "S028",
|
| 459 |
+
"dataset": "spelling",
|
| 460 |
+
"category": "hamza_prefix",
|
| 461 |
+
"input_text": "فالانسان يحتاج للعلم",
|
| 462 |
+
"expected": "فالإنسان يحتاج للعلم",
|
| 463 |
+
"severity": "major",
|
| 464 |
+
"pipeline_corrected": "فالانسان يحتاج للعلم.",
|
| 465 |
+
"pipeline_suggestions": 1,
|
| 466 |
+
"pipeline_ms": 5749,
|
| 467 |
+
"spelling_ms": 3787,
|
| 468 |
+
"grammar_ms": 484,
|
| 469 |
+
"punctuation_ms": 692,
|
| 470 |
+
"verdict": "FP",
|
| 471 |
+
"detail": "Wrong correction"
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"id": "S029",
|
| 475 |
+
"dataset": "spelling",
|
| 476 |
+
"category": "hamza_prefix",
|
| 477 |
+
"input_text": "كالاطفال في اللعب",
|
| 478 |
+
"expected": "كالأطفال في اللعب",
|
| 479 |
+
"severity": "major",
|
| 480 |
+
"pipeline_corrected": "كلا الأطفال في اللعب.",
|
| 481 |
+
"pipeline_suggestions": 2,
|
| 482 |
+
"pipeline_ms": 6739,
|
| 483 |
+
"spelling_ms": 4640,
|
| 484 |
+
"grammar_ms": 701,
|
| 485 |
+
"punctuation_ms": 540,
|
| 486 |
+
"verdict": "FP",
|
| 487 |
+
"detail": "Wrong correction"
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"id": "S030",
|
| 491 |
+
"dataset": "spelling",
|
| 492 |
+
"category": "hamza_prefix",
|
| 493 |
+
"input_text": "للاسف لم ينجح",
|
| 494 |
+
"expected": "للأسف لم ينجح",
|
| 495 |
+
"severity": "major",
|
| 496 |
+
"pipeline_corrected": "للأسف لم ينجح.",
|
| 497 |
+
"pipeline_suggestions": 2,
|
| 498 |
+
"pipeline_ms": 4198,
|
| 499 |
+
"spelling_ms": 2413,
|
| 500 |
+
"grammar_ms": 437,
|
| 501 |
+
"punctuation_ms": 476,
|
| 502 |
+
"verdict": "FP",
|
| 503 |
+
"detail": "Wrong correction"
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"id": "S031",
|
| 507 |
+
"dataset": "spelling",
|
| 508 |
+
"category": "ta_marbuta",
|
| 509 |
+
"input_text": "المدرسه كبيره وجميله",
|
| 510 |
+
"expected": "المدرسة كبيرة وجميلة",
|
| 511 |
+
"severity": "major",
|
| 512 |
+
"pipeline_corrected": "المدرسة كبيرة وجميلة.",
|
| 513 |
+
"pipeline_suggestions": 3,
|
| 514 |
+
"pipeline_ms": 3680,
|
| 515 |
+
"spelling_ms": 1927,
|
| 516 |
+
"grammar_ms": 494,
|
| 517 |
+
"punctuation_ms": 654,
|
| 518 |
+
"verdict": "TP",
|
| 519 |
+
"detail": "Partial improvement"
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"id": "S032",
|
| 523 |
+
"dataset": "spelling",
|
| 524 |
+
"category": "ta_marbuta",
|
| 525 |
+
"input_text": "الجامعه في القاهره",
|
| 526 |
+
"expected": "الجامعة في القاهرة",
|
| 527 |
+
"severity": "major",
|
| 528 |
+
"pipeline_corrected": "الجامعة في القاهرة.",
|
| 529 |
+
"pipeline_suggestions": 2,
|
| 530 |
+
"pipeline_ms": 6067,
|
| 531 |
+
"spelling_ms": 4080,
|
| 532 |
+
"grammar_ms": 537,
|
| 533 |
+
"punctuation_ms": 527,
|
| 534 |
+
"verdict": "TP",
|
| 535 |
+
"detail": "Partial improvement"
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"id": "S033",
|
| 539 |
+
"dataset": "spelling",
|
| 540 |
+
"category": "ta_marbuta",
|
| 541 |
+
"input_text": "السياره سريعه جداً",
|
| 542 |
+
"expected": "السيارة سريعة جداً",
|
| 543 |
+
"severity": "major",
|
| 544 |
+
"pipeline_corrected": "السيارة سريعة جداً.",
|
| 545 |
+
"pipeline_suggestions": 3,
|
| 546 |
+
"pipeline_ms": 4645,
|
| 547 |
+
"spelling_ms": 2783,
|
| 548 |
+
"grammar_ms": 595,
|
| 549 |
+
"punctuation_ms": 423,
|
| 550 |
+
"verdict": "TP",
|
| 551 |
+
"detail": "Partial improvement"
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"id": "S034",
|
| 555 |
+
"dataset": "spelling",
|
| 556 |
+
"category": "ta_marbuta",
|
| 557 |
+
"input_text": "الشجره طويله وجميله",
|
| 558 |
+
"expected": "الشجرة طويلة وجميلة",
|
| 559 |
+
"severity": "major",
|
| 560 |
+
"pipeline_corrected": "الشجرة طويلة وجميلة.",
|
| 561 |
+
"pipeline_suggestions": 3,
|
| 562 |
+
"pipeline_ms": 3937,
|
| 563 |
+
"spelling_ms": 2031,
|
| 564 |
+
"grammar_ms": 496,
|
| 565 |
+
"punctuation_ms": 519,
|
| 566 |
+
"verdict": "TP",
|
| 567 |
+
"detail": "Partial improvement"
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"id": "S035",
|
| 571 |
+
"dataset": "spelling",
|
| 572 |
+
"category": "ta_marbuta",
|
| 573 |
+
"input_text": "الحياه صعبه في المدينه",
|
| 574 |
+
"expected": "الحياة صعبة في المدينة",
|
| 575 |
+
"severity": "major",
|
| 576 |
+
"pipeline_corrected": "الحياة صعبة في المدينة.",
|
| 577 |
+
"pipeline_suggestions": 3,
|
| 578 |
+
"pipeline_ms": 4159,
|
| 579 |
+
"spelling_ms": 2357,
|
| 580 |
+
"grammar_ms": 535,
|
| 581 |
+
"punctuation_ms": 577,
|
| 582 |
+
"verdict": "TP",
|
| 583 |
+
"detail": "Partial improvement"
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"id": "S036",
|
| 587 |
+
"dataset": "spelling",
|
| 588 |
+
"category": "ta_marbuta",
|
| 589 |
+
"input_text": "المكتبه قريبه من البيت",
|
| 590 |
+
"expected": "المكتبة قريبة من البيت",
|
| 591 |
+
"severity": "major",
|
| 592 |
+
"pipeline_corrected": "المكتبة قريبة من البيت.",
|
| 593 |
+
"pipeline_suggestions": 3,
|
| 594 |
+
"pipeline_ms": 5008,
|
| 595 |
+
"spelling_ms": 3269,
|
| 596 |
+
"grammar_ms": 597,
|
| 597 |
+
"punctuation_ms": 503,
|
| 598 |
+
"verdict": "TP",
|
| 599 |
+
"detail": "Partial improvement"
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"id": "S037",
|
| 603 |
+
"dataset": "spelling",
|
| 604 |
+
"category": "ta_marbuta",
|
| 605 |
+
"input_text": "الغرفه نظيفه ومرتبه",
|
| 606 |
+
"expected": "الغرفة نظيفة ومرتبة",
|
| 607 |
+
"severity": "major",
|
| 608 |
+
"pipeline_corrected": "الغرفة نظيفة ومرتبة.",
|
| 609 |
+
"pipeline_suggestions": 3,
|
| 610 |
+
"pipeline_ms": 2678,
|
| 611 |
+
"spelling_ms": 811,
|
| 612 |
+
"grammar_ms": 653,
|
| 613 |
+
"punctuation_ms": 459,
|
| 614 |
+
"verdict": "TP",
|
| 615 |
+
"detail": "Partial improvement"
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"id": "S038",
|
| 619 |
+
"dataset": "spelling",
|
| 620 |
+
"category": "ta_marbuta",
|
| 621 |
+
"input_text": "القصه مثيره للاهتمام",
|
| 622 |
+
"expected": "القصة مثيرة للاهتمام",
|
| 623 |
+
"severity": "major",
|
| 624 |
+
"pipeline_corrected": "القصة مثيرة للاهتمام!",
|
| 625 |
+
"pipeline_suggestions": 3,
|
| 626 |
+
"pipeline_ms": 2345,
|
| 627 |
+
"spelling_ms": 526,
|
| 628 |
+
"grammar_ms": 536,
|
| 629 |
+
"punctuation_ms": 599,
|
| 630 |
+
"verdict": "TP",
|
| 631 |
+
"detail": "Partial improvement"
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"id": "S039",
|
| 635 |
+
"dataset": "spelling",
|
| 636 |
+
"category": "ta_marbuta",
|
| 637 |
+
"input_text": "الرحله طويله ومتعبه",
|
| 638 |
+
"expected": "الرحلة طويلة ومتعبة",
|
| 639 |
+
"severity": "major",
|
| 640 |
+
"pipeline_corrected": "الرحلة طويلة ومتعبة.",
|
| 641 |
+
"pipeline_suggestions": 3,
|
| 642 |
+
"pipeline_ms": 2842,
|
| 643 |
+
"spelling_ms": 993,
|
| 644 |
+
"grammar_ms": 615,
|
| 645 |
+
"punctuation_ms": 478,
|
| 646 |
+
"verdict": "TP",
|
| 647 |
+
"detail": "Partial improvement"
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"id": "S040",
|
| 651 |
+
"dataset": "spelling",
|
| 652 |
+
"category": "ta_marbuta",
|
| 653 |
+
"input_text": "الوظيفه صعبه لكنها مفيده",
|
| 654 |
+
"expected": "الوظيفة صعبة لكنها مفيدة",
|
| 655 |
+
"severity": "major",
|
| 656 |
+
"pipeline_corrected": "الوظيفة صعبة لكنها مفيدة.",
|
| 657 |
+
"pipeline_suggestions": 3,
|
| 658 |
+
"pipeline_ms": 2828,
|
| 659 |
+
"spelling_ms": 824,
|
| 660 |
+
"grammar_ms": 496,
|
| 661 |
+
"punctuation_ms": 759,
|
| 662 |
+
"verdict": "TP",
|
| 663 |
+
"detail": "Partial improvement"
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"id": "S041",
|
| 667 |
+
"dataset": "spelling",
|
| 668 |
+
"category": "ta_marbuta_prefix",
|
| 669 |
+
"input_text": "بالمدرسه الكبيره",
|
| 670 |
+
"expected": "بالمدرسة الكبيرة",
|
| 671 |
+
"severity": "major",
|
| 672 |
+
"pipeline_corrected": "بالمدرسة الكبيرة",
|
| 673 |
+
"pipeline_suggestions": 2,
|
| 674 |
+
"pipeline_ms": 2387,
|
| 675 |
+
"spelling_ms": 782,
|
| 676 |
+
"grammar_ms": 348,
|
| 677 |
+
"punctuation_ms": 477,
|
| 678 |
+
"verdict": "TP",
|
| 679 |
+
"detail": "Exact match"
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"id": "S042",
|
| 683 |
+
"dataset": "spelling",
|
| 684 |
+
"category": "ta_marbuta_prefix",
|
| 685 |
+
"input_text": "والجامعه المصريه",
|
| 686 |
+
"expected": "والجامعة المصرية",
|
| 687 |
+
"severity": "major",
|
| 688 |
+
"pipeline_corrected": "والجامعة المصرية",
|
| 689 |
+
"pipeline_suggestions": 2,
|
| 690 |
+
"pipeline_ms": 2143,
|
| 691 |
+
"spelling_ms": 481,
|
| 692 |
+
"grammar_ms": 441,
|
| 693 |
+
"punctuation_ms": 415,
|
| 694 |
+
"verdict": "TP",
|
| 695 |
+
"detail": "Exact match"
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"id": "S043",
|
| 699 |
+
"dataset": "spelling",
|
| 700 |
+
"category": "ta_marbuta_prefix",
|
| 701 |
+
"input_text": "فالسياره الجديده",
|
| 702 |
+
"expected": "فالسيارة الجديدة",
|
| 703 |
+
"severity": "major",
|
| 704 |
+
"pipeline_corrected": "السيارة الجديدة",
|
| 705 |
+
"pipeline_suggestions": 2,
|
| 706 |
+
"pipeline_ms": 2365,
|
| 707 |
+
"spelling_ms": 764,
|
| 708 |
+
"grammar_ms": 336,
|
| 709 |
+
"punctuation_ms": 402,
|
| 710 |
+
"verdict": "TP",
|
| 711 |
+
"detail": "Partial improvement"
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"id": "S044",
|
| 715 |
+
"dataset": "spelling",
|
| 716 |
+
"category": "ta_marbuta_prefix",
|
| 717 |
+
"input_text": "كالمدرسه القديمه",
|
| 718 |
+
"expected": "كالمدرسة القديمة",
|
| 719 |
+
"severity": "major",
|
| 720 |
+
"pipeline_corrected": "كالمدرسه قديمة",
|
| 721 |
+
"pipeline_suggestions": 1,
|
| 722 |
+
"pipeline_ms": 2443,
|
| 723 |
+
"spelling_ms": 706,
|
| 724 |
+
"grammar_ms": 434,
|
| 725 |
+
"punctuation_ms": 407,
|
| 726 |
+
"verdict": "FP",
|
| 727 |
+
"detail": "Wrong correction"
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"id": "S045",
|
| 731 |
+
"dataset": "spelling",
|
| 732 |
+
"category": "ta_marbuta_prefix",
|
| 733 |
+
"input_text": "للمدرسه الابتدائيه",
|
| 734 |
+
"expected": "للمدرسة الابتدائية",
|
| 735 |
+
"severity": "major",
|
| 736 |
+
"pipeline_corrected": "للمدرسة الابتدائية",
|
| 737 |
+
"pipeline_suggestions": 2,
|
| 738 |
+
"pipeline_ms": 2449,
|
| 739 |
+
"spelling_ms": 770,
|
| 740 |
+
"grammar_ms": 332,
|
| 741 |
+
"punctuation_ms": 661,
|
| 742 |
+
"verdict": "TP",
|
| 743 |
+
"detail": "Exact match"
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"id": "S046",
|
| 747 |
+
"dataset": "spelling",
|
| 748 |
+
"category": "alif_maqsura",
|
| 749 |
+
"input_text": "ذهبت الي المكتبة",
|
| 750 |
+
"expected": "ذهبت إلى المكتبة",
|
| 751 |
+
"severity": "major",
|
| 752 |
+
"pipeline_corrected": "ذهبت إلى المكتبة؟",
|
| 753 |
+
"pipeline_suggestions": 2,
|
| 754 |
+
"pipeline_ms": 2163,
|
| 755 |
+
"spelling_ms": 492,
|
| 756 |
+
"grammar_ms": 435,
|
| 757 |
+
"punctuation_ms": 434,
|
| 758 |
+
"verdict": "TP",
|
| 759 |
+
"detail": "Partial improvement"
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"id": "S047",
|
| 763 |
+
"dataset": "spelling",
|
| 764 |
+
"category": "alif_maqsura",
|
| 765 |
+
"input_text": "المستشفي الكبير",
|
| 766 |
+
"expected": "المستشفى الكبير",
|
| 767 |
+
"severity": "major",
|
| 768 |
+
"pipeline_corrected": "المستشفى الكبير",
|
| 769 |
+
"pipeline_suggestions": 1,
|
| 770 |
+
"pipeline_ms": 1927,
|
| 771 |
+
"spelling_ms": 514,
|
| 772 |
+
"grammar_ms": 336,
|
| 773 |
+
"punctuation_ms": 436,
|
| 774 |
+
"verdict": "TP",
|
| 775 |
+
"detail": "Exact match"
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"id": "S048",
|
| 779 |
+
"dataset": "spelling",
|
| 780 |
+
"category": "alif_maqsura",
|
| 781 |
+
"input_text": "هدي الطالبة ممتاز",
|
| 782 |
+
"expected": "هدى الطالبة ممتاز",
|
| 783 |
+
"severity": "major",
|
| 784 |
+
"pipeline_corrected": "هدى الطالبة ممتازة",
|
| 785 |
+
"pipeline_suggestions": 2,
|
| 786 |
+
"pipeline_ms": 2224,
|
| 787 |
+
"spelling_ms": 443,
|
| 788 |
+
"grammar_ms": 545,
|
| 789 |
+
"punctuation_ms": 436,
|
| 790 |
+
"verdict": "FP",
|
| 791 |
+
"detail": "Wrong correction"
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"id": "S049",
|
| 795 |
+
"dataset": "spelling",
|
| 796 |
+
"category": "alif_maqsura",
|
| 797 |
+
"input_text": "مصطفي طالب مجتهد",
|
| 798 |
+
"expected": "مصطفى طالب مجتهد",
|
| 799 |
+
"severity": "major",
|
| 800 |
+
"pipeline_corrected": "مصطفى طالب مجتهد.",
|
| 801 |
+
"pipeline_suggestions": 2,
|
| 802 |
+
"pipeline_ms": 2224,
|
| 803 |
+
"spelling_ms": 589,
|
| 804 |
+
"grammar_ms": 534,
|
| 805 |
+
"punctuation_ms": 320,
|
| 806 |
+
"verdict": "FP",
|
| 807 |
+
"detail": "Wrong correction"
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"id": "S050",
|
| 811 |
+
"dataset": "spelling",
|
| 812 |
+
"category": "alif_maqsura",
|
| 813 |
+
"input_text": "موسي نبي عظيم",
|
| 814 |
+
"expected": "موسى نبي عظيم",
|
| 815 |
+
"severity": "major",
|
| 816 |
+
"pipeline_corrected": "موسى نبي عظيم.",
|
| 817 |
+
"pipeline_suggestions": 2,
|
| 818 |
+
"pipeline_ms": 1946,
|
| 819 |
+
"spelling_ms": 521,
|
| 820 |
+
"grammar_ms": 438,
|
| 821 |
+
"punctuation_ms": 318,
|
| 822 |
+
"verdict": "FP",
|
| 823 |
+
"detail": "Wrong correction"
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"id": "S051",
|
| 827 |
+
"dataset": "spelling",
|
| 828 |
+
"category": "alif_maqsura",
|
| 829 |
+
"input_text": "علي يدرس في الكلية",
|
| 830 |
+
"expected": "علي يدرس في الكلية",
|
| 831 |
+
"severity": "none",
|
| 832 |
+
"pipeline_corrected": "علي يدرس في الكلية.",
|
| 833 |
+
"pipeline_suggestions": 1,
|
| 834 |
+
"pipeline_ms": 2092,
|
| 835 |
+
"spelling_ms": 516,
|
| 836 |
+
"grammar_ms": 540,
|
| 837 |
+
"punctuation_ms": 455,
|
| 838 |
+
"verdict": "FP",
|
| 839 |
+
"detail": "Modified correct text"
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"id": "S052",
|
| 843 |
+
"dataset": "spelling",
|
| 844 |
+
"category": "alif_maqsura",
|
| 845 |
+
"input_text": "ذهب الي السوق",
|
| 846 |
+
"expected": "ذهب إلى السوق",
|
| 847 |
+
"severity": "major",
|
| 848 |
+
"pipeline_corrected": "ذهب إلى السوق.",
|
| 849 |
+
"pipeline_suggestions": 2,
|
| 850 |
+
"pipeline_ms": 2033,
|
| 851 |
+
"spelling_ms": 604,
|
| 852 |
+
"grammar_ms": 408,
|
| 853 |
+
"punctuation_ms": 393,
|
| 854 |
+
"verdict": "TP",
|
| 855 |
+
"detail": "Partial improvement"
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"id": "S053",
|
| 859 |
+
"dataset": "spelling",
|
| 860 |
+
"category": "alif_maqsura",
|
| 861 |
+
"input_text": "بني المبنى الجديد",
|
| 862 |
+
"expected": "بنى المبنى الجديد",
|
| 863 |
+
"severity": "major",
|
| 864 |
+
"pipeline_corrected": "بنى المبنى الجديد.",
|
| 865 |
+
"pipeline_suggestions": 2,
|
| 866 |
+
"pipeline_ms": 2459,
|
| 867 |
+
"spelling_ms": 635,
|
| 868 |
+
"grammar_ms": 436,
|
| 869 |
+
"punctuation_ms": 513,
|
| 870 |
+
"verdict": "FP",
|
| 871 |
+
"detail": "Wrong correction"
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"id": "S054",
|
| 875 |
+
"dataset": "spelling",
|
| 876 |
+
"category": "word_split",
|
| 877 |
+
"input_text": "ذهبت فيالبيت",
|
| 878 |
+
"expected": "ذهبت في البيت",
|
| 879 |
+
"severity": "major",
|
| 880 |
+
"pipeline_corrected": "ذهبت في البيت",
|
| 881 |
+
"pipeline_suggestions": 1,
|
| 882 |
+
"pipeline_ms": 2495,
|
| 883 |
+
"spelling_ms": 836,
|
| 884 |
+
"grammar_ms": 424,
|
| 885 |
+
"punctuation_ms": 490,
|
| 886 |
+
"verdict": "TP",
|
| 887 |
+
"detail": "Exact match"
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"id": "S055",
|
| 891 |
+
"dataset": "spelling",
|
| 892 |
+
"category": "word_split",
|
| 893 |
+
"input_text": "خرج منالمدرسة",
|
| 894 |
+
"expected": "خرج من المدرسة",
|
| 895 |
+
"severity": "major",
|
| 896 |
+
"pipeline_corrected": "خرج منالمدرسة.",
|
| 897 |
+
"pipeline_suggestions": 1,
|
| 898 |
+
"pipeline_ms": 2287,
|
| 899 |
+
"spelling_ms": 611,
|
| 900 |
+
"grammar_ms": 395,
|
| 901 |
+
"punctuation_ms": 552,
|
| 902 |
+
"verdict": "FP",
|
| 903 |
+
"detail": "Wrong correction"
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"id": "S056",
|
| 907 |
+
"dataset": "spelling",
|
| 908 |
+
"category": "word_split",
|
| 909 |
+
"input_text": "بقي عندالباب",
|
| 910 |
+
"expected": "بقي عند الباب",
|
| 911 |
+
"severity": "major",
|
| 912 |
+
"pipeline_corrected": "بقي عندالباب.",
|
| 913 |
+
"pipeline_suggestions": 1,
|
| 914 |
+
"pipeline_ms": 7894,
|
| 915 |
+
"spelling_ms": 682,
|
| 916 |
+
"grammar_ms": 468,
|
| 917 |
+
"punctuation_ms": 408,
|
| 918 |
+
"verdict": "FP",
|
| 919 |
+
"detail": "Wrong correction"
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"id": "S057",
|
| 923 |
+
"dataset": "spelling",
|
| 924 |
+
"category": "word_split",
|
| 925 |
+
"input_text": "جلس عندالنافذة",
|
| 926 |
+
"expected": "جلس عند النافذة",
|
| 927 |
+
"severity": "major",
|
| 928 |
+
"pipeline_corrected": "جلس عندالنافذة.",
|
| 929 |
+
"pipeline_suggestions": 1,
|
| 930 |
+
"pipeline_ms": 2314,
|
| 931 |
+
"spelling_ms": 540,
|
| 932 |
+
"grammar_ms": 488,
|
| 933 |
+
"punctuation_ms": 435,
|
| 934 |
+
"verdict": "FP",
|
| 935 |
+
"detail": "Wrong correction"
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"id": "S058",
|
| 939 |
+
"dataset": "spelling",
|
| 940 |
+
"category": "word_split",
|
| 941 |
+
"input_text": "رجع الىالبيت",
|
| 942 |
+
"expected": "رجع إلى البيت",
|
| 943 |
+
"severity": "major",
|
| 944 |
+
"pipeline_corrected": "رجع الىالبيت.",
|
| 945 |
+
"pipeline_suggestions": 1,
|
| 946 |
+
"pipeline_ms": 2280,
|
| 947 |
+
"spelling_ms": 659,
|
| 948 |
+
"grammar_ms": 437,
|
| 949 |
+
"punctuation_ms": 380,
|
| 950 |
+
"verdict": "FP",
|
| 951 |
+
"detail": "Wrong correction"
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"id": "S059",
|
| 955 |
+
"dataset": "spelling",
|
| 956 |
+
"category": "word_split",
|
| 957 |
+
"input_text": "خرج منالباب الخلفي",
|
| 958 |
+
"expected": "خرج من الباب الخلفي",
|
| 959 |
+
"severity": "major",
|
| 960 |
+
"pipeline_corrected": "خرج من الباب الخلفي.",
|
| 961 |
+
"pipeline_suggestions": 2,
|
| 962 |
+
"pipeline_ms": 5938,
|
| 963 |
+
"spelling_ms": 512,
|
| 964 |
+
"grammar_ms": 487,
|
| 965 |
+
"punctuation_ms": 554,
|
| 966 |
+
"verdict": "FP",
|
| 967 |
+
"detail": "Wrong correction"
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"id": "S060",
|
| 971 |
+
"dataset": "spelling",
|
| 972 |
+
"category": "word_split",
|
| 973 |
+
"input_text": "نظر الىالسماء",
|
| 974 |
+
"expected": "نظر إلى السماء",
|
| 975 |
+
"severity": "major",
|
| 976 |
+
"pipeline_corrected": "نظر الىالسماء.",
|
| 977 |
+
"pipeline_suggestions": 1,
|
| 978 |
+
"pipeline_ms": 2092,
|
| 979 |
+
"spelling_ms": 653,
|
| 980 |
+
"grammar_ms": 484,
|
| 981 |
+
"punctuation_ms": 327,
|
| 982 |
+
"verdict": "FP",
|
| 983 |
+
"detail": "Wrong correction"
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"id": "S061",
|
| 987 |
+
"dataset": "spelling",
|
| 988 |
+
"category": "correct_text",
|
| 989 |
+
"input_text": "أنا ذهبت إلى الجامعة",
|
| 990 |
+
"expected": "أنا ذهبت إلى الجامعة",
|
| 991 |
+
"severity": "none",
|
| 992 |
+
"pipeline_corrected": "أنا ذهبت إلى الجامعة.",
|
| 993 |
+
"pipeline_suggestions": 1,
|
| 994 |
+
"pipeline_ms": 2067,
|
| 995 |
+
"spelling_ms": 563,
|
| 996 |
+
"grammar_ms": 487,
|
| 997 |
+
"punctuation_ms": 449,
|
| 998 |
+
"verdict": "FP",
|
| 999 |
+
"detail": "Modified correct text"
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"id": "S062",
|
| 1003 |
+
"dataset": "spelling",
|
| 1004 |
+
"category": "correct_text",
|
| 1005 |
+
"input_text": "هذه المدرسة جميلة جداً",
|
| 1006 |
+
"expected": "هذه المدرسة جميلة جداً",
|
| 1007 |
+
"severity": "none",
|
| 1008 |
+
"pipeline_corrected": "هذه المدرسة جميلة جداً.",
|
| 1009 |
+
"pipeline_suggestions": 1,
|
| 1010 |
+
"pipeline_ms": 4721,
|
| 1011 |
+
"spelling_ms": 500,
|
| 1012 |
+
"grammar_ms": 694,
|
| 1013 |
+
"punctuation_ms": 532,
|
| 1014 |
+
"verdict": "FP",
|
| 1015 |
+
"detail": "Modified correct text"
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"id": "S063",
|
| 1019 |
+
"dataset": "spelling",
|
| 1020 |
+
"category": "correct_text",
|
| 1021 |
+
"input_text": "كان الجو ممطراً اليوم",
|
| 1022 |
+
"expected": "كان الجو ممطراً اليوم",
|
| 1023 |
+
"severity": "none",
|
| 1024 |
+
"pipeline_corrected": "كان الجو ممطراً اليوم؟",
|
| 1025 |
+
"pipeline_suggestions": 1,
|
| 1026 |
+
"pipeline_ms": 2771,
|
| 1027 |
+
"spelling_ms": 823,
|
| 1028 |
+
"grammar_ms": 738,
|
| 1029 |
+
"punctuation_ms": 585,
|
| 1030 |
+
"verdict": "FP",
|
| 1031 |
+
"detail": "Modified correct text"
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"id": "S064",
|
| 1035 |
+
"dataset": "spelling",
|
| 1036 |
+
"category": "correct_text",
|
| 1037 |
+
"input_text": "وكان أحمد في المنزل",
|
| 1038 |
+
"expected": "وكان أحمد في المنزل",
|
| 1039 |
+
"severity": "none",
|
| 1040 |
+
"pipeline_corrected": "وكان أحمد في المنزل.",
|
| 1041 |
+
"pipeline_suggestions": 1,
|
| 1042 |
+
"pipeline_ms": 2497,
|
| 1043 |
+
"spelling_ms": 614,
|
| 1044 |
+
"grammar_ms": 499,
|
| 1045 |
+
"punctuation_ms": 659,
|
| 1046 |
+
"verdict": "FP",
|
| 1047 |
+
"detail": "Modified correct text"
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"id": "S065",
|
| 1051 |
+
"dataset": "spelling",
|
| 1052 |
+
"category": "correct_text",
|
| 1053 |
+
"input_text": "إلى اللقاء يا صديقي",
|
| 1054 |
+
"expected": "إلى اللقاء يا صديقي",
|
| 1055 |
+
"severity": "none",
|
| 1056 |
+
"pipeline_corrected": "إلى اللقاء يا صديقي.",
|
| 1057 |
+
"pipeline_suggestions": 1,
|
| 1058 |
+
"pipeline_ms": 6038,
|
| 1059 |
+
"spelling_ms": 665,
|
| 1060 |
+
"grammar_ms": 484,
|
| 1061 |
+
"punctuation_ms": 440,
|
| 1062 |
+
"verdict": "FP",
|
| 1063 |
+
"detail": "Modified correct text"
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"id": "S066",
|
| 1067 |
+
"dataset": "spelling",
|
| 1068 |
+
"category": "correct_text",
|
| 1069 |
+
"input_text": "ذلك الكتاب مفيد جداً",
|
| 1070 |
+
"expected": "ذلك الكتاب مفيد جداً",
|
| 1071 |
+
"severity": "none",
|
| 1072 |
+
"pipeline_corrected": "ذلك الكتاب مفيد جداً.",
|
| 1073 |
+
"pipeline_suggestions": 1,
|
| 1074 |
+
"pipeline_ms": 2372,
|
| 1075 |
+
"spelling_ms": 502,
|
| 1076 |
+
"grammar_ms": 589,
|
| 1077 |
+
"punctuation_ms": 411,
|
| 1078 |
+
"verdict": "FP",
|
| 1079 |
+
"detail": "Modified correct text"
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"id": "S067",
|
| 1083 |
+
"dataset": "spelling",
|
| 1084 |
+
"category": "correct_text",
|
| 1085 |
+
"input_text": "لكن الأمر صعب علينا",
|
| 1086 |
+
"expected": "لكن الأمر صعب علينا",
|
| 1087 |
+
"severity": "none",
|
| 1088 |
+
"pipeline_corrected": "لكن الأمر صعب علينا.",
|
| 1089 |
+
"pipeline_suggestions": 1,
|
| 1090 |
+
"pipeline_ms": 2401,
|
| 1091 |
+
"spelling_ms": 617,
|
| 1092 |
+
"grammar_ms": 485,
|
| 1093 |
+
"punctuation_ms": 424,
|
| 1094 |
+
"verdict": "FP",
|
| 1095 |
+
"detail": "Modified correct text"
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"id": "S068",
|
| 1099 |
+
"dataset": "spelling",
|
| 1100 |
+
"category": "correct_text",
|
| 1101 |
+
"input_text": "هذا أو ذاك سواء عندي",
|
| 1102 |
+
"expected": "هذا أو ذاك سواء عندي",
|
| 1103 |
+
"severity": "none",
|
| 1104 |
+
"pipeline_corrected": "هذا أو ذاك سواء عندي.",
|
| 1105 |
+
"pipeline_suggestions": 1,
|
| 1106 |
+
"pipeline_ms": 6476,
|
| 1107 |
+
"spelling_ms": 636,
|
| 1108 |
+
"grammar_ms": 683,
|
| 1109 |
+
"punctuation_ms": 435,
|
| 1110 |
+
"verdict": "FP",
|
| 1111 |
+
"detail": "Modified correct text"
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"id": "S069",
|
| 1115 |
+
"dataset": "spelling",
|
| 1116 |
+
"category": "correct_text",
|
| 1117 |
+
"input_text": "الطالب المجتهد ينجح دائماً",
|
| 1118 |
+
"expected": "الطالب المجتهد ينجح دا��ماً",
|
| 1119 |
+
"severity": "none",
|
| 1120 |
+
"pipeline_corrected": "الطالب المجتهد ينجح دائماً.",
|
| 1121 |
+
"pipeline_suggestions": 1,
|
| 1122 |
+
"pipeline_ms": 2658,
|
| 1123 |
+
"spelling_ms": 548,
|
| 1124 |
+
"grammar_ms": 645,
|
| 1125 |
+
"punctuation_ms": 579,
|
| 1126 |
+
"verdict": "FP",
|
| 1127 |
+
"detail": "Modified correct text"
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"id": "S070",
|
| 1131 |
+
"dataset": "spelling",
|
| 1132 |
+
"category": "correct_text",
|
| 1133 |
+
"input_text": "العلم نور والجهل ظلام",
|
| 1134 |
+
"expected": "العلم نور والجهل ظلام",
|
| 1135 |
+
"severity": "none",
|
| 1136 |
+
"pipeline_corrected": "العلم نور والجهل ظلام.",
|
| 1137 |
+
"pipeline_suggestions": 1,
|
| 1138 |
+
"pipeline_ms": 2694,
|
| 1139 |
+
"spelling_ms": 608,
|
| 1140 |
+
"grammar_ms": 726,
|
| 1141 |
+
"punctuation_ms": 582,
|
| 1142 |
+
"verdict": "FP",
|
| 1143 |
+
"detail": "Modified correct text"
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"id": "S071",
|
| 1147 |
+
"dataset": "spelling",
|
| 1148 |
+
"category": "correct_text",
|
| 1149 |
+
"input_text": "أحب القراءة والكتابة",
|
| 1150 |
+
"expected": "أحب القراءة والكتابة",
|
| 1151 |
+
"severity": "none",
|
| 1152 |
+
"pipeline_corrected": "أحب القراءة والكتابة.",
|
| 1153 |
+
"pipeline_suggestions": 1,
|
| 1154 |
+
"pipeline_ms": 5967,
|
| 1155 |
+
"spelling_ms": 627,
|
| 1156 |
+
"grammar_ms": 437,
|
| 1157 |
+
"punctuation_ms": 485,
|
| 1158 |
+
"verdict": "FP",
|
| 1159 |
+
"detail": "Modified correct text"
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"id": "S072",
|
| 1163 |
+
"dataset": "spelling",
|
| 1164 |
+
"category": "correct_text",
|
| 1165 |
+
"input_text": "المعلم يشرح الدرس",
|
| 1166 |
+
"expected": "المعلم يشرح الدرس",
|
| 1167 |
+
"severity": "none",
|
| 1168 |
+
"pipeline_corrected": "المعلم يشرح الدرس.",
|
| 1169 |
+
"pipeline_suggestions": 1,
|
| 1170 |
+
"pipeline_ms": 2178,
|
| 1171 |
+
"spelling_ms": 549,
|
| 1172 |
+
"grammar_ms": 431,
|
| 1173 |
+
"punctuation_ms": 466,
|
| 1174 |
+
"verdict": "FP",
|
| 1175 |
+
"detail": "Modified correct text"
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"id": "S073",
|
| 1179 |
+
"dataset": "spelling",
|
| 1180 |
+
"category": "correct_text",
|
| 1181 |
+
"input_text": "ذهبت إلى السوق واشتريت خبزاً",
|
| 1182 |
+
"expected": "ذهبت إلى السوق واشتريت خبزاً",
|
| 1183 |
+
"severity": "none",
|
| 1184 |
+
"pipeline_corrected": "ذهبت إلى السوق واشتريت خبزاً.",
|
| 1185 |
+
"pipeline_suggestions": 1,
|
| 1186 |
+
"pipeline_ms": 3214,
|
| 1187 |
+
"spelling_ms": 720,
|
| 1188 |
+
"grammar_ms": 837,
|
| 1189 |
+
"punctuation_ms": 828,
|
| 1190 |
+
"verdict": "FP",
|
| 1191 |
+
"detail": "Modified correct text"
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"id": "S074",
|
| 1195 |
+
"dataset": "spelling",
|
| 1196 |
+
"category": "correct_text",
|
| 1197 |
+
"input_text": "الطقس جميل في الربيع",
|
| 1198 |
+
"expected": "الطقس جميل في الربيع",
|
| 1199 |
+
"severity": "none",
|
| 1200 |
+
"pipeline_corrected": "الطقس جميل في الربيع.",
|
| 1201 |
+
"pipeline_suggestions": 1,
|
| 1202 |
+
"pipeline_ms": 5596,
|
| 1203 |
+
"spelling_ms": 497,
|
| 1204 |
+
"grammar_ms": 637,
|
| 1205 |
+
"punctuation_ms": 424,
|
| 1206 |
+
"verdict": "FP",
|
| 1207 |
+
"detail": "Modified correct text"
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"id": "S075",
|
| 1211 |
+
"dataset": "spelling",
|
| 1212 |
+
"category": "correct_text",
|
| 1213 |
+
"input_text": "نحن نعمل بجد كل يوم",
|
| 1214 |
+
"expected": "نحن نعمل بجد كل يوم",
|
| 1215 |
+
"severity": "none",
|
| 1216 |
+
"pipeline_corrected": "نحن نعمل بجد كل يوم.",
|
| 1217 |
+
"pipeline_suggestions": 1,
|
| 1218 |
+
"pipeline_ms": 2688,
|
| 1219 |
+
"spelling_ms": 619,
|
| 1220 |
+
"grammar_ms": 785,
|
| 1221 |
+
"punctuation_ms": 360,
|
| 1222 |
+
"verdict": "FP",
|
| 1223 |
+
"detail": "Modified correct text"
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"id": "S076",
|
| 1227 |
+
"dataset": "spelling",
|
| 1228 |
+
"category": "multi_error",
|
| 1229 |
+
"input_text": "انا ذهبت الي المدرسه",
|
| 1230 |
+
"expected": "أنا ذهبت إلى المدرسة",
|
| 1231 |
+
"severity": "critical",
|
| 1232 |
+
"pipeline_corrected": "أنا ذهبت إلى المدرسة.",
|
| 1233 |
+
"pipeline_suggestions": 3,
|
| 1234 |
+
"pipeline_ms": 2497,
|
| 1235 |
+
"spelling_ms": 630,
|
| 1236 |
+
"grammar_ms": 485,
|
| 1237 |
+
"punctuation_ms": 442,
|
| 1238 |
+
"verdict": "TP",
|
| 1239 |
+
"detail": "Partial improvement"
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"id": "S077",
|
| 1243 |
+
"dataset": "spelling",
|
| 1244 |
+
"category": "multi_error",
|
| 1245 |
+
"input_text": "ايضا الجامعه كبيره",
|
| 1246 |
+
"expected": "أيضاً الجامعة كبيرة",
|
| 1247 |
+
"severity": "critical",
|
| 1248 |
+
"pipeline_corrected": "أيضا الجامعة كبيرة.",
|
| 1249 |
+
"pipeline_suggestions": 2,
|
| 1250 |
+
"pipeline_ms": 5834,
|
| 1251 |
+
"spelling_ms": 557,
|
| 1252 |
+
"grammar_ms": 582,
|
| 1253 |
+
"punctuation_ms": 406,
|
| 1254 |
+
"verdict": "TP",
|
| 1255 |
+
"detail": "Partial improvement"
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"id": "S078",
|
| 1259 |
+
"dataset": "spelling",
|
| 1260 |
+
"category": "multi_error",
|
| 1261 |
+
"input_text": "لان المدرسه بعيده جداً",
|
| 1262 |
+
"expected": "لأن المدرسة بعيدة جداً",
|
| 1263 |
+
"severity": "critical",
|
| 1264 |
+
"pipeline_corrected": "لأن المدرسة بعيدة جداً.",
|
| 1265 |
+
"pipeline_suggestions": 4,
|
| 1266 |
+
"pipeline_ms": 2671,
|
| 1267 |
+
"spelling_ms": 669,
|
| 1268 |
+
"grammar_ms": 648,
|
| 1269 |
+
"punctuation_ms": 531,
|
| 1270 |
+
"verdict": "TP",
|
| 1271 |
+
"detail": "Partial improvement"
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"id": "S079",
|
| 1275 |
+
"dataset": "spelling",
|
| 1276 |
+
"category": "multi_error",
|
| 1277 |
+
"input_text": "اين الجامعه الكبيره",
|
| 1278 |
+
"expected": "أين الجامعة الكبيرة",
|
| 1279 |
+
"severity": "critical",
|
| 1280 |
+
"pipeline_corrected": "اين أن الجامعة الكبيرة",
|
| 1281 |
+
"pipeline_suggestions": 2,
|
| 1282 |
+
"pipeline_ms": 2619,
|
| 1283 |
+
"spelling_ms": 710,
|
| 1284 |
+
"grammar_ms": 493,
|
| 1285 |
+
"punctuation_ms": 456,
|
| 1286 |
+
"verdict": "FP",
|
| 1287 |
+
"detail": "Wrong correction"
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"id": "S080",
|
| 1291 |
+
"dataset": "spelling",
|
| 1292 |
+
"category": "multi_error",
|
| 1293 |
+
"input_text": "اول مره ازور المكتبه",
|
| 1294 |
+
"expected": "أول مرة أزور المكتبة",
|
| 1295 |
+
"severity": "critical",
|
| 1296 |
+
"pipeline_corrected": "أول مرة أزور المكتبة.",
|
| 1297 |
+
"pipeline_suggestions": 4,
|
| 1298 |
+
"pipeline_ms": 5759,
|
| 1299 |
+
"spelling_ms": 799,
|
| 1300 |
+
"grammar_ms": 513,
|
| 1301 |
+
"punctuation_ms": 483,
|
| 1302 |
+
"verdict": "TP",
|
| 1303 |
+
"detail": "Partial improvement"
|
| 1304 |
+
}
|
| 1305 |
+
]
|
| 1306 |
+
}
|
tests/v2/test_level2_solo.py
CHANGED
|
@@ -106,22 +106,29 @@ def classify_result(input_text, output_text, expected_text, dataset):
|
|
| 106 |
# For correction tests
|
| 107 |
needs_correction = (inp_n != exp_n)
|
| 108 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 109 |
if needs_correction:
|
| 110 |
if text_changed:
|
| 111 |
-
|
| 112 |
-
if out_n == exp_n:
|
| 113 |
return "TP" # Perfect correction
|
| 114 |
-
elif _edit_distance(
|
| 115 |
return "TP" # Partial but improving correction
|
|
|
|
|
|
|
| 116 |
else:
|
| 117 |
return "FP" # Changed but not in right direction
|
| 118 |
else:
|
| 119 |
return "FN" # Should have corrected but didn't
|
| 120 |
else:
|
| 121 |
-
if text_changed:
|
| 122 |
-
return "FP" # Changed text that was already correct
|
| 123 |
-
else:
|
| 124 |
return "TN" # Correctly left unchanged
|
|
|
|
|
|
|
|
|
|
|
|
|
| 125 |
|
| 126 |
|
| 127 |
def _edit_distance(a, b):
|
|
|
|
| 106 |
# For correction tests
|
| 107 |
needs_correction = (inp_n != exp_n)
|
| 108 |
|
| 109 |
+
# Strip trailing punctuation from output for comparison
|
| 110 |
+
_TERMINAL_PUNCT = '.،؛؟!?!'
|
| 111 |
+
out_stripped = out_n.rstrip(_TERMINAL_PUNCT).rstrip()
|
| 112 |
+
|
| 113 |
if needs_correction:
|
| 114 |
if text_changed:
|
| 115 |
+
if out_n == exp_n or out_stripped == exp_n:
|
|
|
|
| 116 |
return "TP" # Perfect correction
|
| 117 |
+
elif _edit_distance(out_stripped, exp_n) < _edit_distance(inp_n, exp_n):
|
| 118 |
return "TP" # Partial but improving correction
|
| 119 |
+
elif _edit_distance(out_n, exp_n) < _edit_distance(inp_n, exp_n):
|
| 120 |
+
return "TP" # Improving (with punct)
|
| 121 |
else:
|
| 122 |
return "FP" # Changed but not in right direction
|
| 123 |
else:
|
| 124 |
return "FN" # Should have corrected but didn't
|
| 125 |
else:
|
| 126 |
+
if not text_changed:
|
|
|
|
|
|
|
| 127 |
return "TN" # Correctly left unchanged
|
| 128 |
+
elif out_stripped == inp_n:
|
| 129 |
+
return "TN" # Only punctuation added
|
| 130 |
+
else:
|
| 131 |
+
return "FP" # Changed text that was already correct
|
| 132 |
|
| 133 |
|
| 134 |
def _edit_distance(a, b):
|
tests/v2/test_level3_integrated.py
CHANGED
|
@@ -115,11 +115,18 @@ def classify_pipeline(input_text, corrected_text, expected_text, dataset, entity
|
|
| 115 |
# Correction dataset
|
| 116 |
needs_correction = (inp_n != exp_n)
|
| 117 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 118 |
if needs_correction:
|
| 119 |
-
if out_n == exp_n:
|
| 120 |
return "TP", "Exact match"
|
| 121 |
-
elif text_changed and _closer(
|
| 122 |
return "TP", "Partial improvement"
|
|
|
|
|
|
|
| 123 |
elif not text_changed:
|
| 124 |
return "FN", "No correction applied"
|
| 125 |
else:
|
|
@@ -127,6 +134,9 @@ def classify_pipeline(input_text, corrected_text, expected_text, dataset, entity
|
|
| 127 |
else:
|
| 128 |
if not text_changed:
|
| 129 |
return "TN", "Correctly unchanged"
|
|
|
|
|
|
|
|
|
|
| 130 |
else:
|
| 131 |
return "FP", f"Modified correct text"
|
| 132 |
|
|
|
|
| 115 |
# Correction dataset
|
| 116 |
needs_correction = (inp_n != exp_n)
|
| 117 |
|
| 118 |
+
# Strip trailing punctuation from output for comparison
|
| 119 |
+
# Pipeline may add . or ؟ via PuncAra even when the correction is correct
|
| 120 |
+
_TERMINAL_PUNCT = '.،؛؟!?!'
|
| 121 |
+
out_stripped = out_n.rstrip(_TERMINAL_PUNCT).rstrip()
|
| 122 |
+
|
| 123 |
if needs_correction:
|
| 124 |
+
if out_n == exp_n or out_stripped == exp_n:
|
| 125 |
return "TP", "Exact match"
|
| 126 |
+
elif text_changed and _closer(out_stripped, inp_n, exp_n):
|
| 127 |
return "TP", "Partial improvement"
|
| 128 |
+
elif text_changed and _closer(out_n, inp_n, exp_n):
|
| 129 |
+
return "TP", "Partial improvement (with punct)"
|
| 130 |
elif not text_changed:
|
| 131 |
return "FN", "No correction applied"
|
| 132 |
else:
|
|
|
|
| 134 |
else:
|
| 135 |
if not text_changed:
|
| 136 |
return "TN", "Correctly unchanged"
|
| 137 |
+
elif out_stripped == inp_n:
|
| 138 |
+
# Only punctuation was added — count as TN for correction datasets
|
| 139 |
+
return "TN", "Only punctuation added"
|
| 140 |
else:
|
| 141 |
return "FP", f"Modified correct text"
|
| 142 |
|