NLP_Quiz_1

What is the primary goal of using the bag-of-words model in text classification?

• To capture semantic meaning of words

• To represent text data as a matrix of word counts or frequencies

• To predict the next word in a sequence

• To reduce dimensionality of text data

Which loss function is commonly used for binary text classification tasks?

• Mean Squared Error

• Hinge Loss

• Cross-Entropy Loss

• Kullback-Leibler Divergence

Which of the following statements best describes word embeddings like Word2Vec?

• They use one-hot encoding to represent words

• They are designed to replace traditional n-gram models

• They encode the grammatical structure of sentences

• They map words to fixed-size vectors in a continuous vector space based on context

In the context of word embeddings, what does the term "cosine similarity" measure?

• The angle between two word vectors in the vector space, indicating their similarity

• The frequency of co-occurrence of words in a corpus

• The correlation between word vectors and document frequency

• The Euclidean distance between two word vectors

In text classification, what does the term "n-gram" refer to?

• A matrix representation of words

• A model for predicting the next word based on previous words

• A sequence of 'n' contiguous words or characters

• A method for dimensionality reduction

Which of the following is not a common text preprocessing technique?

• • Stemming

• • Lemmatization

• • Stop word removal

• • Part-of-speech tagging

In the context of logistic regression for sentiment analysis, what does the feature X1 represent?

• The frequency of a word in all tweets

• The frequency of a word in negative tweets.

• The frequency of a word in positive tweets.

• The difference in frequency between positive and negative tweets.

The Naive Bayes classifier for sentiment analysis makes a strong assumption about the features. What is this assumption?

• Features are dependent on each other.

• Features are independent of each other.

• Features are normally distributed.

• Features are equally important.

Which of the following is NOT a common probability estimation method used in Naive Bayes for text classification?

• Maximum Likelihood Estimation

• Laplace smoothing

• Kernel Density Estimation

• Log probability

How does Laplace smoothing address the zero probability problem in Naive Bayes?

• By assigning a small positive value to all word counts.

• By ignoring words with zero counts.

• By combining multiple Naive Bayes models.

• By using a different probability estimation method.