Natural Language Processing with Python Updated EditionChapter 111

Chapter 7: Topic Modeling

Section 2 of 3-~ 12 min read-Synced from Cuantum content
  1. What is the primary goal of topic modeling?
  2. - A) To classify text into predefined categories
  • B) To identify the underlying themes or topics in a collection of documents
  • C) To generate summaries of text
  • D) To translate text from one language to another
  1. Which of the following techniques is based on singular value decomposition (SVD)?
  2. - A) Latent Dirichlet Allocation (LDA)
  • B) Hierarchical Dirichlet Process (HDP)
  • C) Latent Semantic Analysis (LSA)
  • D) TextRank
  1. What is a key advantage of Hierarchical Dirichlet Process (HDP) over Latent Dirichlet Allocation (LDA)?
  2. - A) HDP is simpler to implement
  • B) HDP automatically determines the number of topics
  • C) HDP requires less computational resources
  • D) HDP provides more interpretable results
  1. Which library did we use to implement Latent Dirichlet Allocation (LDA) and Hierarchical Dirichlet Process (HDP) in Python?
  2. - A) NLTK
  • B) spaCy
  • C) Gensim
  • D) Scikit-learn
  1. In LDA, what does the term 'topic-word distribution' refer to?
  2. - A) The probability distribution of words in a document
  • B) The probability distribution of topics in a document
  • C) The probability distribution of words given a topic
  • D) The probability distribution of topics given a word