What is the output of the tokenization process in NLP?

A sequence of smaller units such as words, subwords, or characters

A parse tree showing grammatical relationships

A list of stop words removed from the text

A numerical vector representing the entire document

In TF-IDF, why are common words like 'the' and 'is' typically assigned low weights?

They have low term frequency in most documents

They are assigned a fixed weight of zero by the algorithm

They are removed by the tokenizer before TF-IDF is calculated

They appear in many documents, so their inverse document frequency is low

A travel company wants to build a chatbot that can answer questions about booking policies. The chatbot needs to understand user intent from varied phrasings, such as 'Can I cancel?' and 'What is the cancellation policy?' Which NLP approach should they use?

Intent classification using sentence embeddings

Regex patterns for common questions

Keyword matching for 'cancel' and 'policy'

TF-IDF vectorization with cosine similarity

How do word embeddings differ from traditional one-hot encoding?

Embeddings are only used for English text

Embeddings are dense and low-dimensional, while one-hot vectors are sparse and high-dimensional

Embeddings are manually created by linguists

Embeddings are binary, while one-hot vectors are continuous

A search engine for a medical database needs to match the query 'heart attack' to documents containing 'myocardial infarction.' The team wants to tokenize the text in a way that preserves multi-word medical terms. Which tokenization approach should they use?

Word tokenization with n-gram generation

Whitespace tokenization without n-grams

CompTIADataX

Domain 5Objective 2

NLP Concepts DY0-001 Practice Questions (Page 3)

Part of the Specialized applications of data science domain, which accounts for 13% of the DY0-001 exam. CompTIA does not publish an official question count, but from its 165-minute exam (~65–110 total, ~8–14 in this domain), expect 2–4 from this objective — we provide 31 practice questions to prepare you well beyond it. (estimate)

31questions here

7free pages

6concepts

13%of the exam

Questions 11–15

11foundation · easy
What is the output of the tokenization process in NLP?
Select an answer first
12foundation · easy
In TF-IDF, why are common words like 'the' and 'is' typically assigned low weights?
Select an answer first
13application · medium
A travel company wants to build a chatbot that can answer questions about booking policies. The chatbot needs to understand user intent from varied phrasings, such as 'Can I cancel?' and 'What is the cancellation policy?' Which NLP approach should they use?
Select an answer first
14foundation · easy
How do word embeddings differ from traditional one-hot encoding?
Select an answer first
15application · medium
A search engine for a medical database needs to match the query 'heart attack' to documents containing 'myocardial infarction.' The team wants to tokenize the text in a way that preserves multi-word medical terms. Which tokenization approach should they use?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to DY0-001

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by CompTIA. “DY0-001” is a trademark of its owner, used for identification only.