03. NLP

Text preprocessing
  • NLP(1) TokenizationNLP(1) Tokenization
    Posting information


    Posting Date : 01-08-2024
    Last Edit : 01-08-2024
    Writer : KWON Bongjae


    Posting detail

    #01_01 : Tokenization



    #_01_01_01 : Word Tokenization

    from nltk.tokenize im...
  • NLP(2) Stemming & Lemmatization Private or Broken Links
    The page you're looking for is either not available or private!
  • NLP(2) Stemming & Lemmatization
  • NLP(3) StopwordNLP(3) Stopword
    Posting information


    Posting Date : 02-08-2024
    Last Edit : 02-08-2024
    Writer : KWON Bongjae


    Posting detail

    #01_03 : Stopword

    from nltk.corpus import stopwords

    from nltk.tokenize import ...
  • NLP(4) Regular ExpressionNLP(4) Regular Expression
    Posting information


    Posting Date : 03-08-2024
    Last Edit : 03-08-2024
    Writer : KWON Bongjae


    Posting detail

    #01_04 : Regular Expression



    import re



    #1) .



    r = re.compile("p..h"...
  • NLP(5) Integer EncodingNLP(5) Integer Encoding
    Posting information


    Posting Date : 04-08-2024
    Last Edit : 05-08-2024
    Writer : KWON Bongjae


    Posting detail

    #01_05 : Integer Encoding



    #1) using dictionary

    from nltk.tokenize import s...
  • NLP(6) PaddingNLP(6) Padding
    Posting information


    Posting Date : 05-08-2024
    Last Edit : 05-08-2024
    Writer : KWON Bongjae


    Posting detail

    #01_06 : Padding



    import numpy as np

    from tensorflow.keras.preprocessing.te...
  • NLP(7) One Hot EncodingNLP(7) One Hot Encoding
    Posting information


    Posting Date : 05-08-2024
    Last Edit : 05-08-2024
    Writer : KWON Bongjae


    Posting detail

    from konlpy.tag import Okt



    okt = Okt()

    tokens = okt.morphs("만약 우리가 함께 할 수 ...
  • NLP(8) Splitting DataNLP(8) Splitting Data
    Posting information


    Posting Date : 05-08-2024
    Last Edit : 05-08-2024
    Writer : KWON Bongjae


    Posting detail

    #01_08 : Splitting Data



    import pandas as pd

    import numpy as np

    from sklea...
  • NLP(9) Korean Text Preprocessing ToolsNLP(9) Korean Text Preprocessing Tools
    Posting information


    Posting Date : 05-08-2024
    Last Edit : 05-08-2024
    Writer : KWON Bongjae


    Posting detail

    #01_09 Korean Text Preprocessing Tools



    #spcing with pykospacing



    story ...


Language Model
  • NLP(10) Language modelNLP(10) Language model
    Posting information


    Posting Date : 06-08-2024
    Last Edit : 06-08-2024
    Writer : KWON Bongjae


    Posting detail

    Language Model (LM) is a model that assigns probabilities to word sequences(sent...