Text tokenization (Tokenizer) in TensorFlow - ML Experiment: Train & Evaluate

Experiment - Text tokenization (Tokenizer)

Problem:You want to convert text data into numbers so a machine learning model can understand it. Currently, the tokenizer splits text but does not limit the vocabulary size or handle out-of-vocabulary words well.

Current Metrics:Vocabulary size: 10000, OOV token not used, sample tokenized output: ['I', 'love', 'machine', 'learning'] -> [1, 2, 3, 4]

Issue:The tokenizer creates a very large vocabulary which can cause slow training and overfitting. Also, it does not handle words outside the training set, leading to errors during prediction.

Your Task

Improve the tokenizer by limiting the vocabulary size to 5000 and adding an out-of-vocabulary (OOV) token to handle unknown words gracefully.

Use TensorFlow's Tokenizer class

Do not change the input text data

Keep the tokenizer fitting and text-to-sequence conversion steps

Hint 1

Hint 2

Hint 3

Solution

TensorFlow

import tensorflow as tf

texts = [
    'I love machine learning',
    'Deep learning is fun',
    'Natural language processing with TensorFlow',
    'Tokenization converts text to numbers'
]

# Create tokenizer with vocabulary limit and OOV token
tokenizer = tf.keras.preprocessing.text.Tokenizer(num_words=5000, oov_token='<OOV>')

# Fit tokenizer on texts
tokenizer.fit_on_texts(texts)

# Convert texts to sequences
sequences = tokenizer.texts_to_sequences(texts)

# Print word index and sequences
print('Word index:', tokenizer.word_index)
print('Sequences:', sequences)

Added num_words=5000 to limit vocabulary size

Added oov_token='<OOV>' to handle unknown words

Kept fitting and sequence conversion steps the same

Results Interpretation

Before: Vocabulary size was 10000 with no OOV token. Unknown words caused errors or were ignored.

After: Vocabulary size limited to 5000 and OOV token added. Unknown words are replaced by OOV token index, preventing errors.

Limiting vocabulary size reduces model complexity and training time. Adding an OOV token helps the model handle words it has not seen before, improving robustness.

Bonus Experiment

Try using the tokenizer with a larger dataset and experiment with different vocabulary sizes (e.g., 1000, 10000) to see how it affects the tokenization and model input.

💡 Hint

Observe how smaller vocabularies increase OOV token usage and larger vocabularies increase model size and training time.

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