Q#1: Natural Language Processing (NLP) is:
(A) The study of interactions between computers and human language
(B) The study of only programming languages
(C) BFS only
(D) DFS only
Answer: (A) The study of interactions between computers and human language
Q#2: Tokenization in NLP refers to:
(A) Splitting text into words or sentences
(B) Parsing only
(C) BFS only
(D) DFS only
Answer: (A) Splitting text into words or sentences
Q#3: Stemming reduces words to:
(A) Their root forms
(B) Random substrings
(C) BFS only
(D) DFS only
Answer: (A) Their root forms
Q#4: Lemmatization reduces words to:
(A) Their dictionary base form
(B) Random substrings
(C) BFS only
(D) DFS only
Answer: (A) Their dictionary base form
Q#5: Part-of-Speech (POS) tagging assigns:
(A) Grammatical categories to words
(B) Random tags
(C) BFS only
(D) DFS only
Answer: (A) Grammatical categories to words
Q#6: Named Entity Recognition (NER) identifies:
(A) Entities like names, dates, and locations in text
(B) Random words only
(C) BFS only
(D) DFS only
Answer: (A) Entities like names, dates, and locations in text
Q#7: Bag-of-Words (BoW) represents text by:
(A) Word frequency counts ignoring order
(B) Word order only
(C) BFS only
(D) DFS only
Answer: (A) Word frequency counts ignoring order
Q#8: TF-IDF measures:
(A) Importance of a word in a document relative to a corpus
(B) Random values only
(C) BFS only
(D) DFS only
Answer: (A) Importance of a word in a document relative to a corpus
Q#9: Word embeddings represent words as:
(A) Dense vectors capturing semantic meaning
(B) Sparse counts only
(C) BFS only
(D) DFS only
Answer: (A) Dense vectors capturing semantic meaning
Q#10: Word2Vec is used for:
(A) Learning word embeddings
(B) Tokenization only
(C) BFS only
(D) DFS only
Answer: (A) Learning word embeddings
Q#11: Syntax parsing produces:
(A) Parse trees representing grammatical structure
(B) Only tokens
(C) BFS only
(D) DFS only
Answer: (A) Parse trees representing grammatical structure
Q#12: Dependency parsing identifies:
(A) Relationships between words in a sentence
(B) Random connections only
(C) BFS only
(D) DFS only
Answer: (A) Relationships between words in a sentence
Q#13: N-grams are:
(A) Sequences of n consecutive words or characters
(B) Random substrings only
(C) BFS only
(D) DFS only
Answer: (A) Sequences of n consecutive words or characters
Q#14: Language models predict:
(A) Probability of word sequences
(B) Only random words
(C) BFS only
(D) DFS only
Answer: (A) Probability of word sequences
Q#15: Unigram model considers:
(A) Each word independently
(B) Pairs of words
(C) BFS only
(D) DFS only
Answer: (A) Each word independently
Q#16: Bigram model considers:
(A) Pairs of consecutive words
(B) Single words only
(C) BFS only
(D) DFS only
Answer: (A) Pairs of consecutive words
Q#17: Trigram model considers:
(A) Triplets of consecutive words
(B) Single words only
(C) BFS only
(D) DFS only
Answer: (A) Triplets of consecutive words
Q#18: Neural language models use:
(A) Neural networks to predict word probabilities
(B) Only counts
(C) BFS only
(D) DFS only
Answer: (A) Neural networks to predict word probabilities
Q#19: Recurrent Neural Networks (RNNs) are suitable for:
(A) Sequential data like text
(B) Images only
(C) BFS only
(D) DFS only
Answer: (A) Sequential data like text
Q#20: LSTM networks handle:
(A) Long-range dependencies in sequences
(B) Only short sequences
(C) BFS only
(D) DFS only
Answer: (A) Long-range dependencies in sequences
Q#21: GRU is a variant of:
(A) RNN with gating mechanisms
(B) CNN only
(C) BFS only
(D) DFS only
Answer: (A) RNN with gating mechanisms
Q#22: Attention mechanism in NLP:
(A) Focuses on relevant parts of input sequence
(B) Ignores all context
(C) BFS only
(D) DFS only
Answer: (A) Focuses on relevant parts of input sequence
Q#23: Transformers are based on:
(A) Self-attention mechanisms
(B) Only RNNs
(C) BFS only
(D) DFS only
Answer: (A) Self-attention mechanisms
Q#24: BERT is a:
(A) Pretrained transformer model for NLP tasks
(B) Bag-of-words method
(C) BFS only
(D) DFS only
Answer: (A) Pretrained transformer model for NLP tasks
Q#25: GPT models are:
(A) Autoregressive language models
(B) Only sequence taggers
(C) BFS only
(D) DFS only
Answer: (A) Autoregressive language models
Q#26: Tokenization for transformers uses:
(A) Subword units like WordPiece or Byte-Pair Encoding (BPE)
(B) Only whitespace splitting
(C) BFS only
(D) DFS only
Answer: (A) Subword units like WordPiece or Byte-Pair Encoding (BPE)
Q#27: Sentiment analysis predicts:
(A) Emotions or opinions expressed in text
(B) Syntax only
(C) BFS only
(D) DFS only
Answer: (A) Emotions or opinions expressed in text
Q#28: Named entity recognition (NER) is used for:
(A) Extracting proper nouns and entities
(B) Sentence segmentation only
(C) BFS only
(D) DFS only
Answer: (A) Extracting proper nouns and entities
Q#29: Part-of-speech (POS) tagging helps with:
(A) Identifying grammatical roles of words
(B) Only sentiment analysis
(C) BFS only
(D) DFS only
Answer: (A) Identifying grammatical roles of words
Q#30: Machine translation converts:
(A) Text from one language to another
(B) Only tokens to numbers
(C) BFS only
(D) DFS only
Answer: (A) Text from one language to another
Q#31: Sequence-to-sequence (Seq2Seq) models are used for:
(A) Machine translation and summarization
(B) Only tokenization
(C) BFS only
(D) DFS only
Answer: (A) Machine translation and summarization
Q#32: Beam search is used in NLP for:
(A) Decoding sequences efficiently
(B) Random guessing
(C) BFS only
(D) DFS only
Answer: (A) Decoding sequences efficiently
Q#33: Language understanding includes:
(A) Parsing, semantics, and pragmatics
(B) Only tokenization
(C) BFS only
(D) DFS only
Answer: (A) Parsing, semantics, and pragmatics
Q#34: Text classification assigns:
(A) Categories to text documents
(B) Only words
(C) BFS only
(D) DFS only
Answer: (A) Categories to text documents
Q#35: Information retrieval retrieves:
(A) Relevant documents for a query
(B) Only keywords
(C) BFS only
(D) DFS only
Answer: (A) Relevant documents for a query
Q#36: Word sense disambiguation resolves:
(A) Correct meaning of a word in context
(B) Only POS tags
(C) BFS only
(D) DFS only
Answer: (A) Correct meaning of a word in context
Q#37: Coreference resolution identifies:
(A) When different expressions refer to the same entity
(B) BFS only
(C) DFS only
(D) Only tokens
Answer: (A) When different expressions refer to the same entity
Q#38: Question answering systems:
(A) Provide answers to natural language questions
(B) Only classify text
(C) BFS only
(D) DFS only
Answer: (A) Provide answers to natural language questions
Q#39: Text summarization generates:
(A) Short summaries of longer texts
(B) Random sentences
(C) BFS only
(D) DFS only
Answer: (A) Short summaries of longer texts
Q#40: Topic modeling discovers:
(A) Hidden themes in a collection of documents
(B) Only keywords
(C) BFS only
(D) DFS only
Answer: (A) Hidden themes in a collection of documents
Q#41: Named entity linking maps:
(A) Mentions in text to entries in a knowledge base
(B) BFS only
(C) DFS only
(D) Only POS tags
Answer: (A) Mentions in text to entries in a knowledge base
Q#42: Pretrained language models improve:
(A) Performance across multiple NLP tasks
(B) Only token counts
(C) BFS only
(D) DFS only
Answer: (A) Performance across multiple NLP tasks
Q#43: Fine-tuning a language model:
(A) Adapts a pretrained model to a specific task
(B) BFS only
(C) DFS only
(D) Trains from scratch only
Answer: (A) Adapts a pretrained model to a specific task
Q#44: Text generation models predict:
(A) Next words or sentences given context
(B) Only syntax trees
(C) BFS only
(D) DFS only
Answer: (A) Next words or sentences given context
Q#45: Question answering can be:
(A) Extractive or generative
(B) BFS only
(C) DFS only
(D) Only classification
Answer: (A) Extractive or generative
Q#46: Language models are evaluated using:
(A) Perplexity, BLEU, ROUGE, or accuracy
(B) Only token counts
(C) BFS only
(D) DFS only
Answer: (A) Perplexity, BLEU, ROUGE, or accuracy
Q#47: Semantic parsing maps:
(A) Natural language to structured meaning representations
(B) Only words
(C) BFS only
(D) DFS only
Answer: (A) Natural language to structured meaning representations
Q#48: Dialogue systems manage:
(A) Conversations with users in natural language
(B) Only tokenization
(C) BFS only
(D) DFS only
Answer: (A) Conversations with users in natural language
Q#49: NLP faces challenges like:
(A) Ambiguity, context understanding, and language variation
(B) Only tokenization
(C) BFS only
(D) DFS only
Answer: (A) Ambiguity, context understanding, and language variation
Q#50: The main goal of NLP is:
(A) Enable computers to understand, interpret, and generate human language
(B) Memorize text only
(C) BFS only
(D) DFS only
Answer: (A) Enable computers to understand, interpret, and generate human language