Text tokenization (Tokenizer) in TensorFlow - Model Pipeline Trace

Model Pipeline - Text tokenization (Tokenizer)

This pipeline shows how raw text is turned into numbers that a machine learning model can understand. It uses a tokenizer to split sentences into words or pieces, then converts them into numbers. These numbers are used to train a model that learns to predict or classify text.

Data Flow - 4 Stages

1Raw Text Input

1000 sentences→Input raw text data as sentences→1000 sentences

"I love machine learning", "TensorFlow is great"

↓

2Text Tokenization

1000 sentences→Split sentences into tokens (words or subwords)→1000 sentences x variable tokens

"I love machine learning" -> ["I", "love", "machine", "learning"]

↓

3Token to Integer Mapping

1000 sentences x variable tokens→Convert tokens to integer IDs using tokenizer vocabulary→1000 sentences x variable tokens (integers)

["I", "love", "machine", "learning"] -> [12, 45, 78, 90]

↓

4Padding/Truncation

1000 sentences x variable tokens→Pad or truncate token sequences to fixed length (e.g., 10 tokens)→1000 sentences x 10 tokens

[12, 45, 78, 90] -> [12, 45, 78, 90, 0, 0, 0, 0, 0, 0]

Training Trace - Epoch by Epoch

Loss
1.0 |****
0.8 |****
0.6 |*** 
0.4 |**  
0.2 |*   
0.0 +----
      1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.85	0.60	Model starts learning from tokenized input
2	0.65	0.72	Loss decreases, accuracy improves as model learns patterns
3	0.50	0.80	Model shows good learning progress
4	0.40	0.85	Loss continues to decrease, accuracy rises
5	0.35	0.88	Training converges with good accuracy

Prediction Trace - 4 Layers

Layer 1: Input raw text

Layer 2: Tokenization

Layer 3: Token to integer mapping

Layer 4: Padding

Model Quiz - 3 Questions

What does the tokenizer do to the raw text?

A Removes all punctuation only

B Splits text into smaller pieces called tokens

C Converts numbers into words

D Changes text into images

Key Insight

Tokenization transforms text into numbers so models can learn patterns. Padding ensures consistent input size. Training shows loss decreasing and accuracy increasing, meaning the model is learning well from tokenized text.

Practice

1. What is the main purpose of using a Tokenizer in TensorFlow text processing?

easy

A. To convert text into sequences of numbers representing words

B. To train a neural network model directly

C. To visualize text data as images

D. To generate random text samples

Solution

1. Step 1: Understand Tokenizer's role

   A Tokenizer converts words into numbers so models can understand text.

2. Step 2: Identify correct purpose

   It does not train models or create images; it prepares text data by numbering words.

3. Final Answer:

   To convert text into sequences of numbers representing words -> Option A

4. Quick Check:

   Tokenizer = text to numbers [OK]

Hint: Tokenizer turns words into numbers for models [OK]

Common Mistakes:

• Thinking Tokenizer trains the model
• Confusing tokenization with image processing
• Assuming Tokenizer generates text

2. Which of the following is the correct way to create a Tokenizer in TensorFlow?

easy

A. tokenizer = tf.keras.Tokenizer()

B. tokenizer = tf.text.Tokenizer()

C. tokenizer = tf.keras.preprocessing.text.Tokenizer()

D. tokenizer = tf.preprocessing.text.Tokenizer()

Solution

1. Step 1: Recall TensorFlow Tokenizer import path

   The Tokenizer class is in tf.keras.preprocessing.text.

2. Step 2: Match correct syntax

   tokenizer = tf.keras.preprocessing.text.Tokenizer() matches the correct full path and syntax to create a Tokenizer.

3. Final Answer:

   tokenizer = tf.keras.preprocessing.text.Tokenizer() -> Option C

4. Quick Check:

   Correct import path = tokenizer = tf.keras.preprocessing.text.Tokenizer() [OK]

Hint: Tokenizer is under tf.keras.preprocessing.text [OK]

Common Mistakes:

• Using tf.text instead of tf.keras.preprocessing.text
• Missing 'preprocessing' in the path
• Calling Tokenizer directly from tf.keras

3. Given the code:

from tensorflow.keras.preprocessing.text import Tokenizer
texts = ['hello world', 'hello tensorflow']
tokenizer = Tokenizer()
tokenizer.fit_on_texts(texts)
sequences = tokenizer.texts_to_sequences(['hello tensorflow world'])
print(sequences)

What is the output?

medium

A. [[2, 1, 3]]

B. [[1, 3, 2]]

C. [[1, 2, 3]]

D. [[3, 1, 2]]

Solution

1. Step 1: Understand word index assignment

   Tokenizer assigns indexes by frequency descending, ties by order of appearance: 'hello' (2 times) = 1, 'world' (1 time, first) = 2, 'tensorflow' (1 time) = 3.

2. Step 2: Convert text to sequence

   Input 'hello tensorflow world' maps to [1, 3, 2] based on the word index.

3. Final Answer:

   [[1, 3, 2]] -> Option B

4. Quick Check:

   Word order preserved, indexes assigned by frequency then appearance [OK]

Hint: Tokenizer indexes by frequency, then maps words [OK]

Common Mistakes:

• Assuming index order is alphabetical
• Mixing word indexes
• Forgetting Tokenizer fits before sequences

4. What is wrong with this code snippet?

from tensorflow.keras.preprocessing.text import Tokenizer
tokenizer = Tokenizer()
texts = ['cat dog', 'dog mouse']
sequences = tokenizer.texts_to_sequences(texts)
print(sequences)

medium

A. Tokenizer is not imported correctly

B. texts variable is not a list

C. texts_to_sequences expects a list of integers

D. Tokenizer is used before fitting on texts

Solution

1. Step 1: Check Tokenizer usage order

   Tokenizer must be fitted on texts before converting texts to sequences.

2. Step 2: Identify missing fit_on_texts call

   The code misses tokenizer.fit_on_texts(texts) before texts_to_sequences.

3. Final Answer:

   Tokenizer is used before fitting on texts -> Option D

4. Quick Check:

   Fit before sequence conversion [OK]

Hint: Always call fit_on_texts before texts_to_sequences [OK]

Common Mistakes:

• Skipping fit_on_texts call
• Confusing input types for texts_to_sequences
• Assuming texts_to_sequences fits automatically

5. You want to limit your Tokenizer to only the top 3 most frequent words in your texts. Which code correctly sets this limit and converts the text 'apple banana apple orange' to sequences?

hard

A. tokenizer = Tokenizer(num_words=3)
tokenizer.fit_on_texts(['apple banana apple orange'])
print(tokenizer.texts_to_sequences(['apple banana apple orange']))

B. tokenizer = Tokenizer(num_words=4)
tokenizer.fit_on_texts(['apple banana apple orange'])
print(tokenizer.texts_to_sequences(['apple banana apple orange']))

C. tokenizer = Tokenizer(num_words=3)
tokenizer.fit_on_texts(['apple banana orange'])
print(tokenizer.texts_to_sequences(['apple banana apple orange']))

D. tokenizer = Tokenizer(num_words=2)
tokenizer.fit_on_texts(['apple banana apple orange'])
print(tokenizer.texts_to_sequences(['apple banana apple orange']))

Solution

1. Step 1: Understand num_words parameter

   Setting num_words=3 limits tokenizer to top 3 frequent words.

2. Step 2: Fit on full text and convert sequences

   Fitting on the full text with 'apple' (2 times), 'banana' (1), 'orange' (1) ranks 'apple', 'banana', 'orange' as top 3.

3. Step 3: Check output sequence

   Sequence maps 'apple' to 1, 'banana' to 2, 'orange' to 3; output is [[1, 2, 1, 3]].

4. Final Answer:

   tokenizer = Tokenizer(num_words=3) tokenizer.fit_on_texts(['apple banana apple orange']) print(tokenizer.texts_to_sequences(['apple banana apple orange'])) -> Option A

5. Quick Check:

   num_words limits vocab size correctly [OK]

Hint: Use num_words to limit vocabulary size [OK]

Common Mistakes:

• Setting num_words too low or too high
• Fitting on incomplete text
• Confusing num_words with maxlen