NLP-TP2-1315

NLP is the integration of ​

i)AI,

ii)ML,

iii)Linguistic ​ ​

• ii and iii
• iii and i
• i, ii and iii
• i and ii

What is a key challenge in NLP?

i)Ambiguity,

ii)Data Privacy,

iii)Computational Power

• ii only

• i only

• i, ii and iii

• i and ii

Which of the following techniques is used in NLP?

i)Tokenization,

ii)Clustering,

iii)Neural Networks

• i and iii

• ii and iii

• i, ii and iii

• i only

The main purpose of using Regular Expressions in ​ NILP is ​ and ​ ​ ​ ​

• To detect named entities

• To classify documents

• To convert text into speech

• To identify patterns in text

Tokenize the word “Apple” using stemming, the resultant word is _____

• Appl

• Apple

• Error

"The patient was admitted on 12/05/2023 and discharged on 15-05-2023."
Which regular expression correctly matches both dates regardless of whether they use / or - as separators?

• \d{2}[-/]\d{2}[-/]\d{4}

• \d{2}[-|/]\d{2}[-|/]\d{4}

• \d{2}(/|-)\d{2}(/|-)\d{4}

• \d{2}[\/-]\d{2}[\/-]\d{4}

In morphological analysis, if "unbelievable" is decomposed into its morphemes, which of the following is the correct breakdown?

• Root: "un", Suffix: "believable"

• Prefix: "un", Root: "believe", Suffix: "able"

• Prefix: "un", Root: "believ", Suffix: "able"

• Prefix: "un", Root: "believe", Suffix: "ble"

"Dr. Smith's email is [e-mail]."
Which tokenization strategy would best preserve semantic meaning for an NLP email classification task?

• Split by spaces only

• Use regex to split on non-alphanumeric characters

• Apply a rule-based tokenizer that keeps email addresses

• Character-level tokenization

In the sentence "Flying planes can be dangerous", why might POS tagging algorithms produce ambiguity?

• "Flying" could be a verb or adjective

• "Planes" could be a noun or verb

• POS tagging never produces ambiguity

If a language model uses trigrams, how would it estimate the probability of the sentence "I love natural language processing"?

• Multiply probabilities of all single words

• Multiply conditional probabilities of each word given the previous two word

• Multiply probabilities of all bigrams

• Use the maximum frequency unigram