텍스트 전처리 기초

토큰화란 무엇인가요?

파이썬 토큰화 예시

from nltk.tokenize import word_tokenize, sent_tokenize

# Example text
text = "Tokenization is a key step in NLP. Let's learn it!"

# Word Tokenization
word_tokens = word_tokenize(text)
print("Word Tokens:", word_tokens)

# Sentence Tokenization
sentence_tokens = sent_tokenize(text)
print("Sentence Tokens:", sentence_tokens)

정규화란 무엇인가요?

소문자화 및 문장 부호 제거

import string

# Example text
text = "Normalization in NLP is Important!"

# Lowercasing
text = text.lower()

# Removing Punctuation
text = text.translate(str.maketrans('', '', string.punctuation))
print("Normalized Text:", text)

어간 추출과 표제어 추출

from nltk.stem import PorterStemmer, WordNetLemmatizer

# Example text
word = "running"

# Stemming
stemmer = PorterStemmer()
print("Stemmed Word:", stemmer.stem(word))

# Lemmatization
lemmatizer = WordNetLemmatizer()
print("Lemmatized Word:", lemmatizer.lemmatize(word, pos='v'))

불용어 제거

from nltk.corpus import stopwords

# Example text
text = "This is a simple NLP example."

# Tokenize text
words = word_tokenize(text)

# Remove stopwords
stop_words = set(stopwords.words('english'))
filtered_words = [word for word in words if word.lower() not in stop_words]
print("Filtered Words:", filtered_words)

텍스트 전처리의 과제

요약 및 다음 단계