1. . Natural Language Processing (NLP) is:
(A) Compressing datasets only
(B) Encrypting text data only
(C) A branch of AI that focuses on the interaction between computers and human language
(D) Backup only
2. . Tokenization in NLP refers to:
(A) Encrypting tokens
(B) Splitting text into smaller units like words or sentences
(C) Compressing text
(D) Backup only
3. . Stemming in NLP is:
(A) Backup only
(B) Encrypting words
(C) Compressing words
(D) Reducing words to their root form (e.g., "running" → "run")
4. . Lemmatization differs from stemming because it:
(A) Backup only
(B) Encrypts words
(C) Compresses words
(D) Converts words to their base or dictionary form considering context
5. . Stop words in NLP are:
(A) Compressing words
(B) Encrypting words
(C) Commonly used words like "the", "is", "and" which are often removed during preprocessing
(D) Backup only
6. . Bag-of-Words (BoW) is:
(A) Backup only
(B) Encrypting words
(C) Compressing text
(D) A representation of text as a collection of word frequencies ignoring grammar and order
7. . TF-IDF stands for:
(A) Term Frequency-Inverse Document Frequency, used to weigh word importance
(B) Encrypting words
(C) Compressing features
(D) Backup only
8. . Word embeddings like Word2Vec or GloVe are used to:
(A) Represent words as dense vectors capturing semantic meaning
(B) Encrypt vectors
(C) Compress vectors
(D) Backup only
9. . Named Entity Recognition (NER) is:
(A) Compressing text
(B) Encrypting entities
(C) Identifying and classifying entities like names, locations, and dates in text
(D) Backup only
10. . Part-of-Speech (POS) tagging assigns:
(A) Encrypts POS tags
(B) Grammatical labels such as noun, verb, adjective to words in a sentence
(C) Compresses tags
(D) Backup only
11. . Sentiment analysis in NLP aims to:
(A) Encrypt text
(B) Determine the emotion or opinion expressed in text
(C) Compress data
(D) Backup only
12. . Sequence-to-Sequence (Seq2Seq) models are used for:
(A) Machine translation, text summarization, and chatbots
(B) Encrypting sequences
(C) Compressing sequences
(D) Backup only
13. . Attention mechanism in NLP allows:
(A) Compressing sequences
(B) Encrypting attention
(C) The model to focus on relevant parts of the input sequence for better predictions
(D) Backup only
14. . Transformers are:
(A) Encrypting transformers
(B) Deep learning models based entirely on attention mechanisms for NLP tasks
(C) Compressing models
(D) Backup only
15. . BERT is:
(A) Encrypting BERT
(B) A pre-trained transformer model for understanding context in NLP tasks
(C) Compressing BERT
(D) Backup only
16. . GPT models are used for:
(A) Encrypting text
(B) Text generation, summarization, and conversational AI
(C) Compressing text
(D) Backup only
17. . Text preprocessing in NLP typically includes:
(A) Backup only
(B) Encrypting text
(C) Compressing data
(D) Tokenization, stop word removal, stemming, lemmatization, and normalization
18. . Cosine similarity in NLP is used to:
(A) Compress similarity
(B) Encrypt similarity
(C) Measure similarity between two text vectors
(D) Backup only
19. . N-grams in NLP represent:
(A) Backup only
(B) Encrypting sequences
(C) Compressing sequences
(D) Contiguous sequences of N words used for text modeling
20. . The main purpose of NLP is to:
(A) Enable machines to understand, interpret, and generate human language effectively
(B) Encrypt all text
(C) Compress datasets
(D) Backup only