Token Classification
Transformers
ONNX
Safetensors
English
distilbert
resume-parsing
ner
resume
cv
information-extraction
Instructions to use oksomu/resume-ner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use oksomu/resume-ner with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="oksomu/resume-ner")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("oksomu/resume-ner") model = AutoModelForTokenClassification.from_pretrained("oksomu/resume-ner", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Somasundaram Ayyappan Claude Opus 4.6 (1M context) commited on
Commit ·
1652579
1
Parent(s): 03116a3
Add noise augmentation for OCR robustness training
Browse filesGenerates 2 noisy variants per training example by applying:
- Separator swaps (| ↔ + ↔ - ↔ ● at 20% per token)
- Character corruption on O-tagged tokens (5%) and entities (3%)
- Token merging to simulate missing spaces (3%)
- Random case changes on non-entity tokens (5%)
- Random line break insertion (2%)
Training data grows from 3647 → 10941 with augmentation.
BIO tag alignment preserved through all transforms.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- training/generate_from_structured.py +10 -0
- training/noise_augment.py +153 -0
training/generate_from_structured.py
CHANGED
|
@@ -280,6 +280,15 @@ def main():
|
|
| 280 |
|
| 281 |
clean, duplicates_removed = dedupe_examples(clean)
|
| 282 |
train, val = stable_split_examples(clean, train_ratio=0.85)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 283 |
write_dataset(
|
| 284 |
train,
|
| 285 |
val,
|
|
@@ -292,6 +301,7 @@ def main():
|
|
| 292 |
"manual_templates": len(manual),
|
| 293 |
"long_resumes": len(long_resumes),
|
| 294 |
"resume_resource": len(resume_resource),
|
|
|
|
| 295 |
"duplicates_removed": duplicates_removed,
|
| 296 |
},
|
| 297 |
},
|
|
|
|
| 280 |
|
| 281 |
clean, duplicates_removed = dedupe_examples(clean)
|
| 282 |
train, val = stable_split_examples(clean, train_ratio=0.85)
|
| 283 |
+
|
| 284 |
+
try:
|
| 285 |
+
from training.noise_augment import augment_examples
|
| 286 |
+
except ModuleNotFoundError:
|
| 287 |
+
from noise_augment import augment_examples
|
| 288 |
+
|
| 289 |
+
augmented = augment_examples(train, multiplier=2, seed=42)
|
| 290 |
+
print(f"Noise augmented: {len(augmented)} (from {len(train)} train examples)")
|
| 291 |
+
train = train + augmented
|
| 292 |
write_dataset(
|
| 293 |
train,
|
| 294 |
val,
|
|
|
|
| 301 |
"manual_templates": len(manual),
|
| 302 |
"long_resumes": len(long_resumes),
|
| 303 |
"resume_resource": len(resume_resource),
|
| 304 |
+
"noise_augmented": len(augmented),
|
| 305 |
"duplicates_removed": duplicates_removed,
|
| 306 |
},
|
| 307 |
},
|
training/noise_augment.py
ADDED
|
@@ -0,0 +1,153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Noise augmentation for training data to improve OCR robustness.
|
| 2 |
+
|
| 3 |
+
Generates noisy variants of clean training examples by applying
|
| 4 |
+
random perturbations that mimic real-world OCR and PDF extraction
|
| 5 |
+
artifacts. Each augmented example preserves BIO tag alignment.
|
| 6 |
+
|
| 7 |
+
Usage:
|
| 8 |
+
from training.noise_augment import augment_examples
|
| 9 |
+
noisy = augment_examples(clean_examples, multiplier=2)
|
| 10 |
+
"""
|
| 11 |
+
|
| 12 |
+
from __future__ import annotations
|
| 13 |
+
|
| 14 |
+
import random
|
| 15 |
+
import re
|
| 16 |
+
import string
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
def _swap_separator(token: str) -> str:
|
| 20 |
+
"""Randomly swap separator characters: | + - ●"""
|
| 21 |
+
seps = {"|": ["+", "-", "●", "•"], "+": ["|", "-", "•"], "-": ["|", "+"], "●": ["|", "+", "•"], "•": ["|", "+", "●"]}
|
| 22 |
+
if token in seps:
|
| 23 |
+
return random.choice(seps[token])
|
| 24 |
+
return token
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
def _corrupt_char(token: str) -> str:
|
| 28 |
+
"""Drop, swap, or insert a random character to mimic OCR errors."""
|
| 29 |
+
if len(token) < 3:
|
| 30 |
+
return token
|
| 31 |
+
i = random.randint(0, len(token) - 1)
|
| 32 |
+
action = random.choice(["drop", "swap", "insert"])
|
| 33 |
+
if action == "drop":
|
| 34 |
+
return token[:i] + token[i + 1:]
|
| 35 |
+
elif action == "swap" and i < len(token) - 1:
|
| 36 |
+
return token[:i] + token[i + 1] + token[i] + token[i + 2:]
|
| 37 |
+
else:
|
| 38 |
+
c = random.choice(string.ascii_lowercase)
|
| 39 |
+
return token[:i] + c + token[i:]
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
def _merge_tokens(tokens: list[str], labels: list[str], idx: int) -> bool:
|
| 43 |
+
"""Merge token at idx with next token (remove space between them)."""
|
| 44 |
+
if idx >= len(tokens) - 1:
|
| 45 |
+
return False
|
| 46 |
+
if labels[idx] != "O" or labels[idx + 1] != "O":
|
| 47 |
+
return False
|
| 48 |
+
tokens[idx] = tokens[idx] + tokens[idx + 1]
|
| 49 |
+
tokens.pop(idx + 1)
|
| 50 |
+
labels.pop(idx + 1)
|
| 51 |
+
return True
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
def augment_one(tokens: list[str], labels: list[str], seed: int | None = None) -> tuple[list[str], list[str]]:
|
| 55 |
+
"""Create one noisy variant of a training example.
|
| 56 |
+
|
| 57 |
+
Applies random subset of noise operations while preserving
|
| 58 |
+
BIO tag alignment. Only modifies O-tagged tokens for safety,
|
| 59 |
+
except separator swaps which can happen anywhere.
|
| 60 |
+
"""
|
| 61 |
+
if seed is not None:
|
| 62 |
+
random.seed(seed)
|
| 63 |
+
|
| 64 |
+
tok = list(tokens)
|
| 65 |
+
lab = list(labels)
|
| 66 |
+
|
| 67 |
+
# 1. Swap separators (20% per separator token)
|
| 68 |
+
for i in range(len(tok)):
|
| 69 |
+
if tok[i] in ("|", "+", "-", "●", "•") and random.random() < 0.2:
|
| 70 |
+
tok[i] = _swap_separator(tok[i])
|
| 71 |
+
|
| 72 |
+
# 2. Corrupt characters in O-tagged tokens (5% chance per token)
|
| 73 |
+
for i in range(len(tok)):
|
| 74 |
+
if lab[i] == "O" and len(tok[i]) >= 3 and random.random() < 0.05:
|
| 75 |
+
tok[i] = _corrupt_char(tok[i])
|
| 76 |
+
|
| 77 |
+
# 3. Corrupt characters in entity tokens (3% chance — lower rate to keep most entities clean)
|
| 78 |
+
for i in range(len(tok)):
|
| 79 |
+
if lab[i] != "O" and len(tok[i]) >= 4 and random.random() < 0.03:
|
| 80 |
+
tok[i] = _corrupt_char(tok[i])
|
| 81 |
+
|
| 82 |
+
# 4. Merge adjacent O tokens (3% chance per pair)
|
| 83 |
+
i = 0
|
| 84 |
+
while i < len(tok) - 1:
|
| 85 |
+
if random.random() < 0.03:
|
| 86 |
+
_merge_tokens(tok, lab, i)
|
| 87 |
+
else:
|
| 88 |
+
i += 1
|
| 89 |
+
|
| 90 |
+
# 5. Random case change on O tokens (5% chance)
|
| 91 |
+
for i in range(len(tok)):
|
| 92 |
+
if lab[i] == "O" and random.random() < 0.05:
|
| 93 |
+
if random.random() < 0.5:
|
| 94 |
+
tok[i] = tok[i].upper()
|
| 95 |
+
else:
|
| 96 |
+
tok[i] = tok[i].lower()
|
| 97 |
+
|
| 98 |
+
# 6. Insert random line-break token between O tokens (2% chance)
|
| 99 |
+
inserts = []
|
| 100 |
+
for i in range(len(tok) - 1):
|
| 101 |
+
if lab[i] == "O" and lab[i + 1] == "O" and random.random() < 0.02:
|
| 102 |
+
inserts.append(i + 1)
|
| 103 |
+
for offset, idx in enumerate(inserts):
|
| 104 |
+
tok.insert(idx + offset, "\n")
|
| 105 |
+
lab.insert(idx + offset, "O")
|
| 106 |
+
|
| 107 |
+
return tok, lab
|
| 108 |
+
|
| 109 |
+
|
| 110 |
+
def augment_examples(
|
| 111 |
+
examples: list[dict],
|
| 112 |
+
multiplier: int = 2,
|
| 113 |
+
seed: int = 42,
|
| 114 |
+
) -> list[dict]:
|
| 115 |
+
"""Generate noisy variants of training examples.
|
| 116 |
+
|
| 117 |
+
Args:
|
| 118 |
+
examples: list of {"tokens": [...], "ner_tags": [...], ...}
|
| 119 |
+
multiplier: how many noisy copies per clean example
|
| 120 |
+
seed: random seed for reproducibility
|
| 121 |
+
|
| 122 |
+
Returns:
|
| 123 |
+
List of augmented examples (does NOT include originals)
|
| 124 |
+
"""
|
| 125 |
+
try:
|
| 126 |
+
from training.labels import ID2LABEL, LABEL2ID
|
| 127 |
+
except ModuleNotFoundError:
|
| 128 |
+
from labels import ID2LABEL, LABEL2ID
|
| 129 |
+
|
| 130 |
+
random.seed(seed)
|
| 131 |
+
augmented = []
|
| 132 |
+
|
| 133 |
+
for ex_idx, example in enumerate(examples):
|
| 134 |
+
tokens = example["tokens"]
|
| 135 |
+
labels = [ID2LABEL[tag] for tag in example["ner_tags"]]
|
| 136 |
+
|
| 137 |
+
for copy_idx in range(multiplier):
|
| 138 |
+
aug_tokens, aug_labels = augment_one(
|
| 139 |
+
tokens, labels,
|
| 140 |
+
seed=seed + ex_idx * 1000 + copy_idx,
|
| 141 |
+
)
|
| 142 |
+
aug_example = {
|
| 143 |
+
"tokens": aug_tokens,
|
| 144 |
+
"ner_tags": [LABEL2ID[l] for l in aug_labels],
|
| 145 |
+
}
|
| 146 |
+
if "metadata" in example:
|
| 147 |
+
meta = dict(example["metadata"])
|
| 148 |
+
meta["source_id"] = f"{meta.get('source_id', '')}:aug{copy_idx}"
|
| 149 |
+
meta["group_id"] = meta.get("group_id", "")
|
| 150 |
+
aug_example["metadata"] = meta
|
| 151 |
+
augmented.append(aug_example)
|
| 152 |
+
|
| 153 |
+
return augmented
|