Text Preprocessing DATA-SCIENCE-OPTIMIZE Practice Questions (Page 2)

Questions 6–10

1. 6application · medium

   A team is building a named-entity recognition system for medical records. They need to identify drug names and dosages. Which preprocessing step is essential before feeding tokens into the NER model?

   • AApply part-of-speech tagging to each token.
   • BRemove all stop words before tagging.
   • CConvert all tokens to lowercase.
   • DApply stemming to reduce all tokens to their root form.
   Reveal Solution Discussion Select an answer first
2. 7foundation · easy

   What is the purpose of creating a vocabulary and indexing tokens in NLP?

   • ATo map each token to a unique integer index for model input
   • BTo convert text to lowercase
   • CTo remove stop words from the text
   • DTo split text into sentences
   Reveal Solution Discussion Select an answer first
4. 8foundation · easy

   What is the primary characteristic of stemming compared to lemmatization?

   • AStemming always produces a valid dictionary word
   • BStemming is slower than lemmatization
   • CStemming requires part-of-speech tagging
   • DStemming uses rule-based algorithms that may produce non-dictionary words
   Reveal Solution Discussion Select an answer first
5. 9foundation · easy

   What is the purpose of truncation in sequence preprocessing?

   • ATo convert text to lowercase
   • BTo cut longer sequences down to a fixed maximum length
   • CTo remove stop words
   • DTo add tokens to shorter sequences
   Reveal Solution Discussion Select an answer first
6. 10foundation · easy

   Which of the following is an example of a stemming algorithm?

   • AWordNet lemmatizer
   • BPorter stemmer
   • CBERT tokenizer
   • DRegexp tokenizer
   Reveal Solution Discussion Select an answer first