Multi-class text classification in NLP - Model Pipeline Trace

Model Pipeline - Multi-class text classification

This pipeline takes text data and teaches a model to sort each text into one of several categories. It cleans the text, turns words into numbers, trains a model to learn patterns, and then predicts categories for new texts.

Data Flow - 6 Stages

1Raw Text Input

1000 rows x 1 column→Collect raw text samples with labels→1000 rows x 1 column

"I love sunny days"

↓

2Text Cleaning

1000 rows x 1 column→Lowercase, remove punctuation and stopwords→1000 rows x 1 column

"love sunny days"

↓

3Tokenization and Vectorization

1000 rows x 1 column→Split text into words and convert to numeric vectors using TF-IDF→1000 rows x 5000 columns

[0, 0, 0.3, ..., 0, 0.1, 0]

↓

4Train/Test Split

1000 rows x 5000 columns→Split data into training (80%) and testing (20%) sets→Train: 800 rows x 5000 columns, Test: 200 rows x 5000 columns

Train sample vector: [0, 0, 0.3, ..., 0, 0.1, 0]

↓

5Model Training

Train: 800 rows x 5000 columns→Train a neural network classifier with softmax output→Trained model

Model learns to map vectors to one of 5 classes

↓

6Prediction

Test: 200 rows x 5000 columns→Model predicts class probabilities for each test sample→200 rows x 5 columns (class probabilities)

[0.1, 0.7, 0.05, 0.1, 0.05]

Training Trace - Epoch by Epoch

Loss
1.5 |************
1.2 |*********
1.0 |*******
0.85|******
0.75|*****
0.68|****
0.62|***
0.58|**
0.55|*
0.53|

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.5	0.40	Model starts learning, accuracy is low
2	1.2	0.55	Loss decreases, accuracy improves
3	1.0	0.65	Model learns better patterns
4	0.85	0.72	Steady improvement in accuracy
5	0.75	0.78	Model converging well
6	0.68	0.82	Good accuracy reached
7	0.62	0.85	Model fine-tuning
8	0.58	0.87	Accuracy nearing peak
9	0.55	0.88	Small improvements
10	0.53	0.89	Training stabilizes

Prediction Trace - 4 Layers

Layer 1: Input Vector

Layer 2: Hidden Layer with ReLU

Layer 3: Output Layer with Softmax

Layer 4: Prediction

Model Quiz - 3 Questions

What happens to the data shape after tokenization and vectorization?

A It changes from 1000 rows x 1 column to 1000 rows x 5000 columns

B It changes from 1000 rows x 5000 columns to 1000 rows x 1 column

C It stays the same at 1000 rows x 1 column

D It changes to 5000 rows x 1000 columns

Key Insight

This visualization shows how text data is transformed into numbers, then a model learns to classify texts into multiple categories by improving accuracy and lowering loss over time. The softmax layer helps the model choose the most likely class by turning scores into probabilities.

Practice

1. What is the main goal of multi-class text classification?

easy

A. To sort text into multiple categories based on content

B. To translate text into another language

C. To count the number of words in a text

D. To generate new text from a given input

Solution

1. Step 1: Understand the task of multi-class text classification

   This task involves assigning each text sample to one category out of many possible categories.

2. Step 2: Compare options with the task definition

   Only To sort text into multiple categories based on content describes sorting text into multiple categories, which matches the task.

3. Final Answer:

   To sort text into multiple categories based on content -> Option A

4. Quick Check:

   Multi-class classification = sorting into many categories [OK]

Hint: Multi-class means sorting text into many groups [OK]

Common Mistakes:

• Confusing classification with translation
• Thinking it counts words instead of categorizing
• Mixing generation with classification

2. Which of the following is the correct way to represent text data for multi-class classification?

easy

A. Converting text into numerical vectors like TF-IDF or embeddings

B. Using raw text strings directly as input to the model

C. Sorting text alphabetically before training

D. Removing all punctuation and spaces only

Solution

1. Step 1: Identify how models process text

   Models cannot understand raw text strings; they need numbers to learn patterns.

2. Step 2: Check which option converts text to numbers

   Converting text into numerical vectors like TF-IDF or embeddings mentions converting text into numerical vectors like TF-IDF or embeddings, which is correct.

3. Final Answer:

   Converting text into numerical vectors like TF-IDF or embeddings -> Option A

4. Quick Check:

   Text must be numbers for models [OK]

Hint: Models need numbers, not raw text, to learn [OK]

Common Mistakes:

• Feeding raw text directly to models
• Thinking sorting text helps classification
• Ignoring the need for numerical representation

3. Given the following Python code snippet for multi-class text classification, what will be the output of print(predicted_class)?

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.naive_bayes import MultinomialNB

texts = ["I love cats", "Dogs are great", "I hate rain"]
labels = ["positive", "positive", "negative"]

vectorizer = CountVectorizer()
X = vectorizer.fit_transform(texts)

model = MultinomialNB()
model.fit(X, labels)

new_text = ["I love dogs"]
X_new = vectorizer.transform(new_text)
predicted_class = model.predict(X_new)[0]

medium

A. "neutral"

B. "negative"

C. An error because of unknown words

D. "positive"

Solution

1. Step 1: Understand training data and labels

   The model is trained on texts labeled as "positive" or "negative". "I love cats" and "Dogs are great" are positive, "I hate rain" is negative.

2. Step 2: Predict class for new text "I love dogs"

   The new text contains words "I", "love", and "dogs" which appear in positive examples. The model predicts "positive" as the class.

3. Final Answer:

   "positive" -> Option D

4. Quick Check:

   New text matches positive words, so prediction is positive [OK]

Hint: New text similar to positive examples predicts positive [OK]

Common Mistakes:

• Assuming unknown words cause errors
• Choosing negative because of 'dogs' only
• Picking neutral which is not a trained label

4. Identify the error in this multi-class text classification code snippet:

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression

texts = ["happy day", "sad night", "joyful morning"]
labels = ["positive", "negative", "positive"]

vectorizer = TfidfVectorizer()
X = vectorizer.fit_transform(texts)

model = LogisticRegression()
model.fit(texts, labels)

medium

A. Labels should be numbers, not strings

B. Passing raw texts instead of vectorized data to model.fit

C. Using LogisticRegression instead of Naive Bayes

D. TfidfVectorizer cannot be used with LogisticRegression

Solution

1. Step 1: Check input to model.fit()

   The model.fit() method expects numerical features, but raw texts are passed instead of vectorized data.

2. Step 2: Identify correct input

   The vectorized data X should be passed to model.fit, not the original texts.

3. Final Answer:

   Passing raw texts instead of vectorized data to model.fit -> Option B

4. Quick Check:

   Model needs numbers, not raw text, for training [OK]

Hint: Model.fit needs vectorized data, not raw text [OK]

Common Mistakes:

• Passing raw text directly to model.fit
• Thinking label type causes error here
• Believing vectorizer choice causes this error

5. You have a dataset with 5 classes and highly imbalanced text samples per class. Which approach best improves multi-class classification performance?

hard

A. Use only the most frequent class for prediction

B. Ignore imbalance and train model on raw data

C. Use class weighting or oversampling to balance training data

D. Remove classes with fewer samples to simplify problem

Solution

1. Step 1: Understand class imbalance impact

   Imbalanced classes cause models to favor majority classes, reducing accuracy on minority classes.

2. Step 2: Identify best practice to handle imbalance

   Using class weighting or oversampling balances the training data, helping the model learn all classes better.

3. Final Answer:

   Use class weighting or oversampling to balance training data -> Option C

4. Quick Check:

   Balance data to improve multi-class model accuracy [OK]

Hint: Balance classes with weighting or oversampling [OK]

Common Mistakes:

• Ignoring imbalance and expecting good results
• Removing minority classes loses valuable data
• Predicting only the majority class ignores others