RNN-based text generation in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the RNN layer from TensorFlow Keras.

NLP

from tensorflow.keras.layers import [1]

Drag options to blanks, or click blank then click option'

ASimpleRNN

BDense

CConv2D

DMaxPooling2D

Attempts:

3 left

💡 Hint

Common Mistakes

Importing Dense instead of SimpleRNN

Confusing convolutional layers with RNN layers

The SimpleRNN layer is used for building recurrent neural networks for sequence data.

2fill in blank

medium

Complete the code to define an RNN model with an embedding layer and a SimpleRNN layer.

NLP

model = Sequential([
    Embedding(input_dim=1000, output_dim=64),
    [1](128),
    Dense(1000, activation='softmax')
])

Drag options to blanks, or click blank then click option'

AConv1D

BDropout

CLSTM

DSimpleRNN

Attempts:

3 left

💡 Hint

Common Mistakes

Using Conv1D instead of a recurrent layer

Using Dropout where a recurrent layer is needed

SimpleRNN is the recurrent layer used here to process the embedded sequences.

3fill in blank

hard

Fix the error in the code to compile the RNN model for text generation.

NLP

model.compile(optimizer='adam', loss=[1], metrics=['accuracy'])

Drag options to blanks, or click blank then click option'

A'categorical_crossentropy'

B'hinge'

C'binary_crossentropy'

D'mse'

Attempts:

3 left

💡 Hint

Common Mistakes

Using binary_crossentropy for multi-class output

Using mse which is for regression tasks

For multi-class text generation, categorical_crossentropy is the correct loss function.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps words to their lengths only if length is greater than 3.

NLP

word_lengths = {word: [1] for word in words if len(word) [2] 3}

Drag options to blanks, or click blank then click option'

Alen(word)

B<

C>

Dword

Attempts:

3 left

💡 Hint

Common Mistakes

Using the word itself as the value instead of its length

Using less than instead of greater than in the condition

We want the length of each word as the value and only include words longer than 3 characters.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps uppercase words to their counts only if count is greater than 0.

NLP

result = { [1]: [2] for word, count in word_counts.items() if count [3] 0 }

Drag options to blanks, or click blank then click option'

Aword.upper()

Bcount

C>

Dword.lower()

Attempts:

3 left

💡 Hint

Common Mistakes

Using word.lower() instead of word.upper()

Using less than instead of greater than in the condition

We convert words to uppercase as keys, keep counts as values, and filter counts greater than zero.