Hugging Face 토크나이저: BERT용 텍스트 인코딩

Why Tokenisation Matters for BERT

Installing Hugging Face Transformers

# Install dependencies
# pip install transformers datasets torch

from transformers import BertTokenizer
import torch

# Load the pre-trained BERT tokenizer (downloads ~200 KB vocab file)
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
print('Vocabulary size:', tokenizer.vocab_size)  # 30522
print('Max length:', tokenizer.model_max_length)  # 512

Tokenizing a Single Sentence

from transformers import BertTokenizer

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')

text = 'Machine learning is transforming the world.'
encoding = tokenizer(
    text,
    return_tensors='pt',
    truncation=True,
    max_length=128
)

print('input_ids:', encoding['input_ids'])
print('attention_mask:', encoding['attention_mask'])
print('Token count:', encoding['input_ids'].shape[1])

WordPiece Subword Tokenisation

from transformers import BertTokenizer

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')

# Inspect raw tokens before converting to IDs
word = 'tokenisation'
pieces = tokenizer.tokenize(word)
print('WordPiece pieces:', pieces)  # ['token', '##isation']

ids = tokenizer.convert_tokens_to_ids(pieces)
print('IDs:', ids)

# Decode back to text
decoded = tokenizer.decode(ids)
print('Decoded:', decoded)

Batch Tokenisation with Padding

from transformers import BertTokenizer

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')

sentences = [
    'Short.',
    'This is a much longer sentence for demonstration purposes.'
]

encoded = tokenizer(
    sentences,
    padding=True,        # pad to longest in batch
    truncation=True,
    max_length=64,
    return_tensors='pt'
)
print('input_ids shape:', encoded['input_ids'].shape)
print('attention_mask:', encoded['attention_mask'])

Truncation: Handling Long Text

from transformers import BertTokenizer

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')

long_text = 'word ' * 600  # 600 words -- too long for BERT

# Strategy 1: truncate to first 512 tokens
encoded_first = tokenizer(long_text, truncation=True, max_length=512)
print('First 512 length:', len(encoded_first['input_ids']))

# Strategy 2: only take the last 510 tokens + [CLS] + [SEP]
tokens = tokenizer.tokenize(long_text)[-510:]
encoded_last = [tokenizer.cls_token] + tokens + [tokenizer.sep_token]
print('Last-window length:', len(encoded_last))

Sentence-Pair Inputs for BERT

from transformers import BertTokenizer

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')

question = 'Where was Marie Curie born?'
context = 'Marie Curie was born in Warsaw, Poland in 1867.'

encoded = tokenizer(
    question,
    context,
    truncation=True,
    max_length=128,
    return_tensors='pt'
)

print('token_type_ids:', encoded['token_type_ids'])
# 0 = question tokens, 1 = context tokens

AutoTokenizer: Provider-Agnostic Loading

from transformers import AutoTokenizer

# Works for BERT, RoBERTa, DistilBERT, GPT-2, and more
tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')

# Exact same API regardless of model family
text = 'Transfer learning is powerful.'
encoded = tokenizer(text, return_tensors='pt')
print(encoded['input_ids'])

# Switching models is trivial:
# tokenizer = AutoTokenizer.from_pretrained('roberta-base')

Decoding: IDs Back to Text

from transformers import BertTokenizer

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')

text = 'Hello, world!'
ids = tokenizer.encode(text)
print('Encoded IDs:', ids)  # includes [CLS]=101 and [SEP]=102

decoded = tokenizer.decode(ids, skip_special_tokens=True)
print('Decoded text:', decoded)  # 'hello, world!'

decoded_with_special = tokenizer.decode(ids)
print('With special tokens:', decoded_with_special)  # '[CLS] hello, world! [SEP]'

Building a DataLoader for Fine-Tuning

import torch
from torch.utils.data import Dataset, DataLoader
from transformers import BertTokenizer

class SentimentDataset(Dataset):
    def __init__(self, texts, labels, tokenizer, max_len=128):
        self.texts = texts
        self.labels = labels
        self.tokenizer = tokenizer
        self.max_len = max_len

    def __len__(self):
        return len(self.texts)

    def __getitem__(self, idx):
        enc = self.tokenizer(
            self.texts[idx],
            truncation=True, padding='max_length',
            max_length=self.max_len, return_tensors='pt'
        )
        return {
            'input_ids': enc['input_ids'].squeeze(),
            'attention_mask': enc['attention_mask'].squeeze(),
            'label': torch.tensor(self.labels[idx], dtype=torch.long)
        }

Fast Tokenizers and Offset Mapping

from transformers import BertTokenizerFast

tokenizer = BertTokenizerFast.from_pretrained('bert-base-uncased')

text = 'Paris is lovely.'
encoded = tokenizer(text, return_offsets_mapping=True)

for token_id, offset in zip(encoded['input_ids'], encoded['offset_mapping']):
    token = tokenizer.convert_ids_to_tokens([token_id])[0]
    print(f'{token:15s} -> chars {offset}')
# paris           -> chars (0, 5)
# is              -> chars (6, 8)

Quick Check

Lesson Recap