Model selection for tasks in NLP - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Model Choice

intermediate

Choosing the best model for sentiment analysis

You want to build a model that classifies movie reviews as positive or negative. Which model is the best choice for this binary text classification task?

A A convolutional neural network (CNN) designed for image recognition

B A recurrent neural network (RNN) or transformer-based model trained on text data

C A k-means clustering algorithm

D A linear regression model

💡 Hint

Think about models that understand sequences of words and context in text.

RNNs and transformer models are designed to process sequences like text and capture context, making them suitable for sentiment analysis. CNNs for images, clustering, and regression are not appropriate for this task.

❓ Metrics

intermediate

Evaluating a multi-class text classifier

You trained a model to classify news articles into 5 categories. Which metric is best to evaluate overall model performance?

A Accuracy

B Mean Squared Error (MSE)

C BLEU score

D Perplexity

💡 Hint

Consider a metric that measures correct predictions over total predictions for classification.

Accuracy measures the proportion of correct predictions in classification tasks. MSE is for regression, BLEU is for language generation quality, and perplexity measures language model uncertainty.

🧠 Conceptual

advanced

Selecting a model for named entity recognition (NER)

You need to identify names of people, places, and organizations in text. Which model type is most suitable for this sequence labeling task?

A Transformer-based model with token classification head

B Feedforward neural network with bag-of-words input

C K-nearest neighbors classifier

D Autoencoder for dimensionality reduction

💡 Hint

NER requires understanding each word's role in context within a sentence.

Transformer models with token classification heads can label each word in a sequence, making them ideal for NER. Feedforward networks lose sequence order, KNN is not suited for sequence labeling, and autoencoders are for unsupervised tasks.

🔧 Debug

advanced

Why does this text classification model perform poorly?

You trained a text classifier using a bag-of-words model and logistic regression. The accuracy is very low on test data. What is the most likely reason?

A The model is overfitting because it has too many parameters

B The dataset is too large for logistic regression to train

C Bag-of-words ignores word order and context, limiting performance on complex language tasks

D Logistic regression cannot handle binary classification

💡 Hint

Think about what information bag-of-words loses about the text.

Bag-of-words treats text as unordered word counts, losing context and word order, which are important for understanding meaning. Logistic regression can handle binary classification and large datasets, and overfitting usually increases training accuracy.

❓ Hyperparameter

expert

Choosing hyperparameters for fine-tuning a transformer model

You are fine-tuning a pre-trained transformer model on a small labeled dataset for text classification. Which hyperparameter setting is most important to avoid overfitting?

A Train for many epochs without early stopping

B Use a very high learning rate (e.g., 0.1) to speed up training

C Freeze all layers and only train the final classification layer

D Use a small batch size and apply dropout regularization

💡 Hint

Think about techniques that reduce overfitting when data is limited.

Small batch sizes and dropout help regularize training and reduce overfitting. High learning rates can cause unstable training. Training many epochs without stopping risks overfitting. Freezing layers can help but may limit learning capacity.