Exercise 10: Word Sense Disambiguation ....................................................... 20
Sentence Boundary Detection ......................................................................... 21
Exercise 11: Sentence Boundary Detection .................................................... 21
Activity 1: Preprocessing of Raw Text .............................................................. 22
Kick Starting an NLP Project ....................................................................... 23
Data Collection ................................................................................................... 23
Data Preprocessing ............................................................................................ 23
Feature Extraction ............................................................................................. 24
Model Development .......................................................................................... 24
Model Assessment ............................................................................................. 24
Model Deployment ............................................................................................ 24
Summary ....................................................................................................... 24
Basic Feature Extraction Methods 27
Introduction .................................................................................................. 28
Types of Data ................................................................................................ 28
Categorizing Data Based on Structure ............................................................ 28
Categorization of Data Based on Content ...................................................... 30
Cleaning Text Data ....................................................................................... 31
Tokenization ....................................................................................................... 31
Exercise 12: Text Cleaning and Tokenization ................................................. 31
Exercise 13: Extracting n-grams ....................................................................... 33
Exercise 14: Tokenizing Texts with Dierent Packages – Keras
and TextBlob ....................................................................................................... 36
Types of Tokenizers .......................................................................................... 38
Exercise 15: Tokenizing Text Using Various Tokenizers ................................ 38
Issues with Tokenization ................................................................................... 45
Stemming ............................................................................................................ 45
RegexpStemmer ................................................................................................. 45
评论0