RNN for text classification in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the RNN layer from Keras.

NLP

from tensorflow.keras.layers import [1]

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

ADense

BSimpleRNN

CConv2D

DMaxPooling2D

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing Dense which is a fully connected layer, not recurrent.

Choosing Conv2D or MaxPooling2D which are for images.

The SimpleRNN layer is the basic recurrent neural network layer used for sequence data like text.

2fill in blank

medium

Complete the code to add an embedding layer for text input.

NLP

model.add(Embedding(input_dim=[1], output_dim=64, input_length=100))

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

A100

B64

C10

D5000

Attempts:

3 left

💡 Hint

Common Mistakes

Using input_dim equal to output_dim or input_length.

Choosing a very small number like 10 which is too small for vocab size.

input_dim is the size of the vocabulary, typically a larger number like 5000 for text.

3fill in blank

hard

Fix the error in the RNN layer definition to return the last output only.

NLP

model.add(SimpleRNN(32, return_sequences=[1]))

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

AFalse

BTrue

CNone

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Setting return_sequences=True which outputs the full sequence.

Using None or 0 which are invalid values for this parameter.

return_sequences=False makes the RNN output only the last output, suitable for classification.

4fill in blank

hard

Fill both blanks to compile the model with appropriate loss and optimizer for binary classification.

NLP

model.compile(loss=[1], optimizer=[2], metrics=['accuracy'])

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

A'binary_crossentropy'

B'categorical_crossentropy'

C'adam'

D'sgd'

Attempts:

3 left

💡 Hint

Common Mistakes

Using categorical_crossentropy for binary classification.

Using sgd optimizer which may be slower to converge.

For binary classification, use 'binary_crossentropy' loss and 'adam' optimizer for good performance.

5fill in blank

hard

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

NLP

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

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

Aword

Blen(word)

Dlen(words)

Attempts:

3 left

💡 Hint

Common Mistakes

Using len(words) which is the length of the list, not each word.

Using inconsistent variable names in the comprehension.

The comprehension maps each word to its length if the word length is greater than 3.