Multi-class text classification in NLP - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Model Choice

intermediate

Choosing the right model for multi-class text classification

You want to classify news articles into 5 categories based on their text content. Which model is most suitable for this multi-class text classification task?

A A k-means clustering algorithm

B A linear regression model

C A convolutional neural network (CNN) designed for text classification

D A simple decision tree for regression

💡 Hint

Think about models that handle text data and can output multiple classes.

Linear regression and decision trees for regression are for continuous outputs, not categories. K-means is unsupervised clustering, not classification. CNNs can learn patterns in text sequences and are suitable for multi-class classification.

❓ Metrics

intermediate

Evaluating multi-class classification with accuracy

You trained a multi-class text classifier with 4 classes. After testing, you got the following predictions and true labels:

Predictions: [2, 0, 1, 3, 1, 0]
True labels: [2, 0, 0, 3, 1, 1]

What is the accuracy of the model on this test set?

A 0.6667

B 0.5

C 0.8333

D 0.3333

💡 Hint

Accuracy = (number of correct predictions) / (total predictions).

Correct predictions are at indices 0,1,3,4 (4 correct out of 6). Accuracy = 4/6 = 0.6667.

❓ Predict Output

advanced

Output of softmax activation in multi-class classification

Given the logits output from a model for 3 classes: [2.0, 1.0, 0.1], what is the softmax output vector?

NLP

import numpy as np
logits = np.array([2.0, 1.0, 0.1])
exp_logits = np.exp(logits)
softmax = exp_logits / np.sum(exp_logits)
print(np.round(softmax, 3))

A [0.500, 0.300, 0.200]

B [0.659, 0.242, 0.099]

C [0.700, 0.200, 0.100]

D [0.333, 0.333, 0.333]

💡 Hint

Softmax converts logits to probabilities that sum to 1.

Calculating softmax: exp(2)=7.389, exp(1)=2.718, exp(0.1)=1.105. Sum=11.212. Probabilities: 7.389/11.212=0.659, 2.718/11.212=0.242, 1.105/11.212=0.099.

❓ Hyperparameter

advanced

Choosing batch size for training a multi-class text classifier

You are training a multi-class text classification model on a large dataset. Which batch size choice is likely to improve training stability and speed without using too much memory?

A Batch size of 1 (stochastic gradient descent)

B Batch size of 1024 (very large batch)

C Batch size equal to the entire dataset

D Batch size of 32 (moderate size)

💡 Hint

Consider trade-offs between memory, speed, and gradient stability.

Batch size 1 is slow and noisy. Very large batch sizes can cause memory issues and poor generalization. Using the entire dataset is often impractical. Batch size 32 balances speed, memory, and stable gradients.

🔧 Debug

expert

Identifying the cause of poor multi-class classification accuracy

You trained a multi-class text classifier with 6 classes. The training accuracy is 95%, but test accuracy is only 40%. Which issue is most likely causing this problem?

A The model is overfitting the training data

B The test data has fewer classes than training data

C The model is underfitting the training data

D The loss function used is mean squared error

💡 Hint

Think about why training accuracy is high but test accuracy is low.

High training accuracy but low test accuracy indicates overfitting. Underfitting would show low training accuracy. Test data having fewer classes would cause different errors but not this pattern. Mean squared error is not ideal but not the main cause here.