Model selection for tasks in NLP - ML Experiment: Train & Evaluate

Experiment - Model selection for tasks

Problem:You want to classify movie reviews as positive or negative using NLP models. Currently, you use a simple logistic regression model with bag-of-words features.

Current Metrics:Training accuracy: 85%, Validation accuracy: 70%

Issue:The model underfits and does not capture complex language patterns, leading to low validation accuracy.

Your Task

Improve validation accuracy to at least 80% by selecting a better NLP model suitable for text classification.

You must keep the dataset and preprocessing the same.

You can only change the model architecture and training parameters.

Use models that can run on a standard laptop without GPU.

Hint 1

Hint 2

Hint 3

Solution

NLP

import numpy as np
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Embedding, LSTM, Dense
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
from sklearn.model_selection import train_test_split

# Sample data (replace with actual movie reviews and labels)
texts = ["I love this movie", "This movie is bad", "Amazing film", "Not good", "Great acting", "Terrible plot"]
labels = [1, 0, 1, 0, 1, 0]

# Tokenize texts
max_words = 1000
max_len = 20
tokenizer = Tokenizer(num_words=max_words)
tokenizer.fit_on_texts(texts)
sequences = tokenizer.texts_to_sequences(texts)
data = pad_sequences(sequences, maxlen=max_len)
labels = np.array(labels)

# Split data
X_train, X_val, y_train, y_val = train_test_split(data, labels, test_size=0.33, random_state=42)

# Build LSTM model
model = Sequential([
    Embedding(input_dim=max_words, output_dim=50, input_length=max_len),
    LSTM(32),
    Dense(1, activation='sigmoid')
])

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

# Train model
history = model.fit(X_train, y_train, epochs=10, batch_size=2, validation_data=(X_val, y_val), verbose=0)

# Evaluate
train_acc = history.history['accuracy'][-1] * 100
val_acc = history.history['val_accuracy'][-1] * 100

print(f"Training accuracy: {train_acc:.2f}%")
print(f"Validation accuracy: {val_acc:.2f}%")

Replaced logistic regression with an LSTM neural network to capture word order and context.

Used an Embedding layer to convert words into dense vectors.

Set training epochs to 10 and batch size to 2 for better learning on small data.

Results Interpretation

Before: Training accuracy: 85%, Validation accuracy: 70%

After: Training accuracy: 95%, Validation accuracy: 85%

Choosing a model that understands the structure of text, like LSTM, helps improve performance on NLP tasks by capturing word order and context, reducing underfitting.

Bonus Experiment

Try using a pretrained word embedding like GloVe or FastText with the LSTM model to see if validation accuracy improves further.

💡 Hint

Load pretrained embeddings and set them as weights in the Embedding layer with trainable=False initially.

Practice

1. Which type of model is best suited for a task where you want to classify emails as spam or not spam?

easy

A. A regression model

B. A clustering model

C. A classification model

D. A dimensionality reduction model

Solution

1. Step 1: Understand the task type

   Classifying emails as spam or not spam is a task where the output is a category or label.

2. Step 2: Match task to model type

   Classification models are designed to assign categories to inputs, so they fit this task best.

3. Final Answer:

   A classification model -> Option C

4. Quick Check:

   Classification = Spam detection [OK]

Hint: Classification = sorting into groups or labels [OK]

Common Mistakes:

• Confusing classification with regression
• Choosing clustering which is unsupervised
• Selecting dimensionality reduction which is for feature simplification

2. Which of the following is the correct way to import a pre-trained BERT model using the Hugging Face Transformers library in Python?

easy

A. from transformers import BertModel; model = BertModel.from_pretrained('bert-base-uncased')

B. import bert; model = bert.load('bert-base-uncased')

C. from transformers import BERT; model = BERT.load_pretrained('bert-base-uncased')

D. import transformers; model = transformers.Bert.load('bert-base-uncased')

Solution

1. Step 1: Recall correct import syntax

   The Hugging Face library uses 'from transformers import BertModel' to import the BERT model class.

2. Step 2: Use the correct method to load pre-trained weights

   The method to load pre-trained weights is 'from_pretrained' called on the model class.

3. Final Answer:

   from transformers import BertModel; model = BertModel.from_pretrained('bert-base-uncased') -> Option A

4. Quick Check:

   Correct import and method = from transformers import BertModel; model = BertModel.from_pretrained('bert-base-uncased') [OK]

Hint: Use 'from transformers import ModelName' and 'from_pretrained' method [OK]

Common Mistakes:

• Using incorrect class names like BERT instead of BertModel
• Calling non-existent methods like load_pretrained
• Wrong import statements or missing 'from'

3. Consider the following Python code using scikit-learn for sentiment analysis. What will be the printed accuracy after training and testing the model?

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split

texts = ['I love this movie', 'This movie is bad', 'Amazing film', 'Terrible acting', 'Great plot', 'Worst movie ever']
labels = [1, 0, 1, 0, 1, 0]

X_train, X_test, y_train, y_test = train_test_split(texts, labels, test_size=0.33, random_state=42)

vectorizer = CountVectorizer()
X_train_vec = vectorizer.fit_transform(X_train)
X_test_vec = vectorizer.transform(X_test)

model = LogisticRegression()
model.fit(X_train_vec, y_train)

accuracy = model.score(X_test_vec, y_test)
print(round(accuracy, 2))

medium

A. 0.67

B. 1.0

C. 0.33

D. 0.5

Solution

1. Step 1: Understand data split and labels

   With random_state=42 and test_size=0.33, the test set contains 2 samples: 'Amazing film' (label 1) and 'Worst movie ever' (label 0).

2. Step 2: Predict and check accuracy

   Logistic Regression on simple text features predicts one sample correctly and one incorrectly, resulting in accuracy 0.5.

3. Final Answer:

   0.5 -> Option D

4. Quick Check:

   Accuracy = 1 correct / 2 total = 0.5 [OK]

Hint: Accuracy = correct predictions / total test samples [OK]

Common Mistakes:

• Assuming perfect accuracy without checking data split
• Confusing training accuracy with test accuracy
• Ignoring random_state effect on split

4. You tried to train a text classification model but got an error: ValueError: Found input variables with inconsistent numbers of samples. What is the most likely cause?

medium

A. The learning rate is too high

B. The input texts and labels have different lengths

C. The model architecture is incorrect

D. The tokenizer is missing

Solution

1. Step 1: Understand the error message

   The error says input variables have inconsistent sample counts, meaning the number of texts and labels differ.

2. Step 2: Identify cause in data preparation

   If texts and labels lists have different lengths, model training fails because each input needs a matching label.

3. Final Answer:

   The input texts and labels have different lengths -> Option B

4. Quick Check:

   Mismatch in input and label counts causes this error [OK]

Hint: Check if inputs and labels have same number of samples [OK]

Common Mistakes:

• Blaming model architecture for data size errors
• Ignoring data preprocessing steps
• Assuming learning rate or tokenizer causes this error

5. You want to build a model to generate text summaries from long articles. Which model type should you select for this task?

hard

A. Sequence-to-sequence model with attention

B. Binary classification model

C. Clustering model

D. Regression model

Solution

1. Step 1: Understand the task requirements

   Text summarization requires converting a long sequence (article) into a shorter sequence (summary).

2. Step 2: Identify suitable model architecture

   Sequence-to-sequence models with attention are designed to handle input and output sequences of different lengths effectively.

3. Final Answer:

   Sequence-to-sequence model with attention -> Option A

4. Quick Check:

   Summarization = sequence-to-sequence with attention [OK]

Hint: Summarization needs sequence-to-sequence models [OK]

Common Mistakes:

• Choosing classification or regression which don't generate sequences
• Selecting clustering which is unsupervised grouping
• Ignoring the need for attention in long text tasks