Text generation with RNN in TensorFlow - Model Metrics & Evaluation

Metrics & Evaluation - Text generation with RNN

Which metric matters for Text generation with RNN and WHY

For text generation using RNNs, common metrics include perplexity and cross-entropy loss. These measure how well the model predicts the next word or character in a sequence. Lower perplexity means the model is better at guessing the next token, which leads to more natural and coherent text. Accuracy can be used but is less informative because predicting exact next words is hard and many outputs can be valid.

Confusion matrix or equivalent visualization

Text generation is a sequence prediction task with many possible outputs, so confusion matrices are not practical. Instead, we look at loss curves and perplexity scores over training epochs.

Epoch | Training Loss | Validation Loss | Perplexity
-----------------------------------------------
  1   |     2.5       |      2.7       |   12.2
  2   |     2.1       |      2.3       |    9.9
  3   |     1.8       |      2.0       |    7.4
  4   |     1.6       |      1.9       |    6.7
  5   |     1.5       |      1.8       |    6.1
    

This shows the model is improving as loss and perplexity decrease.

Precision vs Recall tradeoff with examples

Precision and recall are less relevant for text generation because the output is open-ended. Instead, there is a tradeoff between creativity and coherence. For example:

• High creativity: The model generates surprising and diverse text but may produce errors or nonsense.
• High coherence: The model produces safe, predictable text but may be boring or repetitive.

This tradeoff can be controlled by parameters like temperature during sampling.

What "good" vs "bad" metric values look like for this use case

Good:

• Low cross-entropy loss (e.g., below 1.5 on validation data)
• Low perplexity (close to 1 means perfect prediction)
• Generated text is fluent, relevant, and context-aware

Bad:

• High loss and perplexity (e.g., above 3 or 4)
• Generated text is random, repetitive, or nonsensical
• Model overfits training data and fails on new prompts

Common pitfalls in metrics for text generation

• Overfitting: Low training loss but high validation loss means the model memorizes training text and can't generalize.
• Ignoring diversity: Only optimizing for loss can lead to dull, repetitive text.
• Using accuracy: Accuracy is misleading because many next words can be correct; it doesn't capture quality well.
• Data leakage: If test data overlaps with training, metrics will be unrealistically good.

Self-check question

Your RNN text generation model has a validation accuracy of 85% but a perplexity of 50. Is this model good for generating text? Why or why not?

Answer: No, this model is not good. The high accuracy is misleading because many next words can be correct, so accuracy is not reliable here. The very high perplexity (50) means the model is very uncertain about the next word predictions, so generated text will likely be poor quality and incoherent.

Key Result

Perplexity and cross-entropy loss are key metrics; lower values mean better text prediction quality.

Practice

1. What is the main purpose of using an RNN in text generation tasks?

easy

A. To sort words alphabetically

B. To count the number of words in a sentence

C. To learn patterns in sequences of words and predict the next word

D. To translate text into images

Solution

1. Step 1: Understand RNN function in text

   RNNs process sequences and learn how words follow each other.

2. Step 2: Identify the goal of text generation

   The goal is to predict the next word based on previous words.

3. Final Answer:

   To learn patterns in sequences of words and predict the next word -> Option C

4. Quick Check:

   RNN predicts next word = B [OK]

Hint: RNNs handle sequences and predict next items [OK]

Common Mistakes:

• Thinking RNNs sort or count words
• Confusing RNN with image processing
• Assuming RNNs translate text directly

2. Which of the following is the correct way to add an embedding layer in a TensorFlow RNN model for text generation?

easy

A. tf.keras.layers.MaxPooling1D(pool_size=2)

B. tf.keras.layers.Dense(units=embedding_dim)

C. tf.keras.layers.Conv2D(filters=embedding_dim, kernel_size=3)

D. tf.keras.layers.Embedding(input_dim=vocab_size, output_dim=embedding_dim)

Solution

1. Step 1: Identify embedding layer syntax

   Embedding layers use input_dim and output_dim to map words to vectors.

2. Step 2: Match correct TensorFlow layer

   tf.keras.layers.Embedding is the correct layer for word embeddings.

3. Final Answer:

   tf.keras.layers.Embedding(input_dim=vocab_size, output_dim=embedding_dim) -> Option D

4. Quick Check:

   Embedding layer uses input_dim and output_dim = A [OK]

Hint: Embedding layer uses input_dim and output_dim parameters [OK]

Common Mistakes:

• Using Dense instead of Embedding for word vectors
• Confusing Conv2D with text embedding
• Applying MaxPooling1D incorrectly for embeddings

3. Given the following code snippet, what will be the shape of the output from the RNN layer?

model = tf.keras.Sequential([
  tf.keras.layers.Embedding(input_dim=1000, output_dim=64),
  tf.keras.layers.SimpleRNN(128, return_sequences=False),
  tf.keras.layers.Dense(1000, activation='softmax')
])

input_shape = (32, 10)  # batch size 32, sequence length 10
output = model(tf.random.uniform(input_shape, maxval=1000, dtype=tf.int32))
print(output.shape)

medium

A. (32, 1000)

B. (32, 10, 128)

C. (10, 128)

D. (32, 128)

Solution

1. Step 1: Analyze RNN layer output shape

   SimpleRNN with return_sequences=False outputs (batch_size, units) = (32, 128).

2. Step 2: Check Dense layer output shape

   Dense layer with 1000 units outputs (32, 1000).

3. Final Answer:

   (32, 1000) -> Option A

4. Quick Check:

   Final output shape = (batch_size, vocab_size) = C [OK]

Hint: return_sequences=False means RNN outputs last step only [OK]

Common Mistakes:

• Confusing return_sequences=True output shape
• Ignoring batch size in output shape
• Mixing RNN units with Dense output units

4. Which of the following statements is CORRECT about this TensorFlow RNN model code for text generation:

model = tf.keras.Sequential([
  tf.keras.layers.Embedding(input_dim=5000, output_dim=64),
  tf.keras.layers.SimpleRNN(128, return_sequences=True),
  tf.keras.layers.Dense(5000, activation='softmax')
])

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy')

# Training data: input sequences of shape (batch_size, seq_length)
# Labels: next word indices of shape (batch_size, seq_length)

model.fit(train_data, train_labels, epochs=5)

medium

A. Loss function sparse_categorical_crossentropy is incorrect for this task

B. Using return_sequences=True but labels shape is (batch_size, seq_length) which is correct

C. Labels shape should be (batch_size,) not (batch_size, seq_length)

D. Embedding layer input_dim is too small

Solution

1. Step 1: Check RNN output and labels shape

   return_sequences=True outputs sequences matching label shape (batch_size, seq_length).

2. Step 2: Verify loss function suitability

   sparse_categorical_crossentropy is correct for integer labels in classification.

3. Final Answer:

   Using return_sequences=True but labels shape is (batch_size, seq_length) which is correct -> Option B

4. Quick Check:

   return_sequences=True matches label shape = A [OK]

Hint: return_sequences=True means labels must be sequences too [OK]

Common Mistakes:

• Assuming labels must be 1D when output is sequence
• Choosing wrong loss function for integer labels
• Changing embedding input_dim unnecessarily

5. You want to generate text using a trained RNN model. Which approach correctly generates new text step-by-step?

hard

A. Feed initial seed text, predict next word, append it, then feed updated text repeatedly

B. Feed entire training dataset at once to get all predictions

C. Use the model to predict all words in one call without updating input

D. Randomly select words without using the model predictions

Solution

1. Step 1: Understand text generation process

   Text generation uses seed text and predicts one word at a time.

2. Step 2: Describe iterative prediction

   After predicting a word, append it to input and predict next word repeatedly.

3. Final Answer:

   Feed initial seed text, predict next word, append it, then feed updated text repeatedly -> Option A

4. Quick Check:

   Stepwise prediction with updated input = D [OK]

Hint: Generate text word-by-word, updating input each time [OK]

Common Mistakes:

• Trying to predict all words at once without feedback
• Ignoring seed text and using random words
• Feeding entire dataset instead of seed for generation