1. What does NLP stand for?
A) Natural Language Processing
B) Neural Language Processing
C) Numerical Language Processing
D) Nonlinear Language Processing
Answer: A) Natural Language Processing
2. Which of the following is a common task in NLP?
A) Sentiment analysis
B) Image classification
C) Time series forecasting
D) Clustering
Answer: A) Sentiment analysis
3. What is “tokenization” in NLP?
A) The process of breaking down text into individual words or phrases
B) The process of encoding text into numerical format
C) The process of translating text into another language
D) The process of summarizing text
Answer: A) The process of breaking down text into individual words or phrases
4. Which technique is used for converting words into numerical vectors in NLP?
A) One-hot encoding
B) K-means clustering
C) Principal Component Analysis (PCA)
D) Convolutional Neural Networks (CNNs)
Answer: A) One-hot encoding
5. What is the purpose of “stemming” in NLP?
A) To reduce words to their base or root form
B) To categorize text into predefined topics
C) To translate text into different languages
D) To correct grammatical errors
Answer: A) To reduce words to their base or root form
6. Which of the following is an example of a “stop word”?
A) “the”
B) “machine”
C) “learning”
D) “model”
Answer: A) “the”
7. What is “Named Entity Recognition” (NER) used for in NLP?
A) To identify and classify entities such as people, organizations, and locations in text
B) To generate new text based on the given input
C) To translate text into another language
D) To summarize large documents
Answer: A) To identify and classify entities such as people, organizations, and locations in text
8. Which model is commonly used for generating word embeddings?
A) Word2Vec
B) K-means clustering
C) Support Vector Machines (SVM)
D) Random Forest
Answer: A) Word2Vec
9. What does the term “n-gram” refer to in NLP?
A) A contiguous sequence of n items from a given text
B) A type of neural network layer
C) A text summarization technique
D) A method for translating languages
Answer: A) A contiguous sequence of n items from a given text
10. Which technique is used to improve text classification accuracy by combining multiple models?
A) Ensemble learning
B) Data augmentation
C) Dimensionality reduction
D) Hyperparameter tuning
Answer: A) Ensemble learning
11. What is “part-of-speech tagging” (POS tagging) in NLP?
A) Assigning parts of speech (e.g., nouns, verbs) to each word in a text
B) Translating text into different languages
C) Summarizing text into shorter sentences
D) Detecting the sentiment of a text
Answer: A) Assigning parts of speech (e.g., nouns, verbs) to each word in a text
12. Which algorithm is often used for text classification tasks in NLP?
A) Naive Bayes
B) Decision Trees
C) K-means clustering
D) Principal Component Analysis (PCA)
Answer: A) Naive Bayes
13. What is “word sense disambiguation” in NLP?
A) The process of determining the correct meaning of a word based on context
B) The process of identifying named entities in text
C) The process of tokenizing text into individual words
D) The process of translating text into another language
Answer: A) The process of determining the correct meaning of a word based on context
14. Which of the following is a common evaluation metric for text classification models?
A) F1-score
B) Mean Squared Error (MSE)
C) Accuracy
D) Root Mean Squared Error (RMSE)
Answer: A) F1-score
15. What does “LSTM” stand for in the context of NLP?
A) Long Short-Term Memory
B) Linear Short-Term Memory
C) Logistic Sequential Temporal Model
D) Layered Statistical Text Model
Answer: A) Long Short-Term Memory
16. Which technique is commonly used for text summarization?
A) Extractive summarization
B) Generative adversarial networks (GANs)
C) K-means clustering
D) Principal Component Analysis (PCA)
Answer: A) Extractive summarization
17. What is “TF-IDF” in NLP?
A) Term Frequency-Inverse Document Frequency, a statistical measure used to evaluate the importance of a word in a document
B) Temporal Frequency-Inverse Document Factor, a method for text classification
C) Textual Frequency-Inverse Data Feature, used for summarization
D) Term Factor-Inverse Document Frequency, a type of embedding
Answer: A) Term Frequency-Inverse Document Frequency, a statistical measure used to evaluate the importance of a word in a document
18. What does “semantic similarity” refer to in NLP?
A) The degree to which two pieces of text have similar meanings
B) The grammatical structure of sentences
C) The number of unique words in a text
D) The syntactic structure of sentences
Answer: A) The degree to which two pieces of text have similar meanings
19. Which of the following models is used for machine translation tasks?
A) Transformer
B) K-means clustering
C) Decision Trees
D) Random Forest
Answer: A) Transformer
20. What is “attention mechanism” in NLP models?
A) A technique that allows the model to focus on different parts of the input text when making predictions
B) A type of data preprocessing
C) A method for feature extraction
D) A type of regularization
Answer: A) A technique that allows the model to focus on different parts of the input text when making predictions
21. What is “contextual embeddings” in NLP?
A) Embeddings that capture the meaning of words based on the context in which they appear
B) Fixed representations of words regardless of context
C) Numerical representations of character sequences
D) Pretrained embeddings used for feature extraction
Answer: A) Embeddings that capture the meaning of words based on the context in which they appear
22. Which of the following is a popular library for NLP tasks in Python?
A) NLTK
B) OpenCV
C) Scikit-learn
D) TensorFlow
Answer: A) NLTK
23. What is “Word2Vec”?
A) A model for learning word embeddings
B) A text classification algorithm
C) A data preprocessing method
D) A type of neural network architecture
Answer: A) A model for learning word embeddings
24. What is “BERT” used for in NLP?
A) A model for generating contextual embeddings
B) A method for tokenization
C) A type of clustering algorithm
D) A feature selection technique
Answer: A) A model for generating contextual embeddings
25. What does “latent semantic analysis” (LSA) aim to achieve?
A) To discover the underlying structure in a collection of texts by analyzing relationships between terms and documents
B) To translate text into different languages
C) To summarize large documents
D) To classify text into predefined categories
Answer: A) To discover the underlying structure in a collection of texts by analyzing relationships between terms and documents
26. Which technique helps in dealing with long-term dependencies in text data?
A) Long Short-Term Memory (LSTM)
B) Principal Component Analysis (PCA)
C) Naive Bayes Classifier
D) K-means clustering
Answer: A) Long Short-Term Memory (LSTM)
27. What is the “bag-of-words” (BoW) model used for?
A) Representing text data as a collection of words without considering the order
B) Generating word embeddings
C) Extracting features from text
D) Tokenizing text into phrases
Answer: A) Representing text data as a collection of words without considering the order
28. Which algorithm is commonly used for topic modeling in NLP?
A) Latent Dirichlet Allocation (LDA)
B) K-means clustering
C) Support Vector Machines (SVM)
D) Random Forest
Answer: A) Latent Dirichlet Allocation (LDA)
29. What does “preprocessing” in NLP typically include?
A) Cleaning and transforming text data before analysis
B) Training a model on the data
C) Evaluating model performance
D) Generating new data
Answer: A) Cleaning and transforming text data before analysis
30. What is “text generation” in NLP?
A) Creating new text based on a given input or model
B) Classifying text into predefined categories
C) Extracting named entities from text
D) Summarizing large documents
Answer: A) Creating new text based on a given input or model
More MCQS on AI Robot
- Basic Electronics and Mechanics MCQs
- Circuit Theory MCQs
- Sensors and Actuators MCQs
- Mechanics and Dynamics MCQs
- Programming MCQs
- Python MCQs
- C/C++ MCQs
- MATLAB MCQs
- Control Systems MCQs
- Introduction to Robotics MCQs
Intermediate Topics:
- Advanced Kinematics and Dynamics MCQs
- Advanced Control Systems MCQs
- Artificial Intelligence and Machine Learning MCQs
- Robotic Operating System (ROS) MCQs
- Embedded Systems MCQs
- Microcontrollers MCQs
- Real-Time Operating Systems (RTOS) MCQs
- Embedded C Programming MCQs
- Path Planning and Navigation MCQs