Why text generation creates content in NLP - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to generate text using a simple model.

NLP

generated_text = model.[1](input_sequence)

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

Apredict

Bgenerate

Cfit

Dcompile

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'fit' instead of 'predict' which trains the model rather than generating output.

Using 'compile' which prepares the model but does not generate output.

The predict method is used to generate output from the model given an input sequence.

2fill in blank

medium

Complete the code to prepare input text for the model.

NLP

input_sequence = tokenizer.[1](raw_text)

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

Adecode

Bfit

Cencode

Dtransform

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'decode' which converts tokens back to text.

Using 'fit' which is for training the tokenizer.

The encode method converts raw text into tokens the model can understand.

3fill in blank

hard

Fix the error in the code to generate text from the model.

NLP

output = model.predict([1])

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

Araw_text

Binput_sequence

Ctokenizer

Dmodel

Attempts:

3 left

💡 Hint

Common Mistakes

Passing raw text directly causes errors.

Passing the tokenizer or model object instead of input data.

The model expects tokenized input, so we must pass input_sequence, not raw text.

4fill in blank

hard

Fill both blanks to convert model output tokens back to readable text.

NLP

decoded_text = tokenizer.[1](output_tokens, [2]=True)

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

Adecode

Bencode

Cskip_special_tokens

Dadd_special_tokens

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'encode' instead of 'decode' reverses the process.

Not skipping special tokens results in extra symbols in output.

Use decode to convert tokens to text and skip_special_tokens=True to remove special tokens.

5fill in blank

hard

Fill all three blanks to generate text and decode it properly.

NLP

input_seq = tokenizer.[1](text)
output_tokens = model.[2](input_seq)
result = tokenizer.[3](output_tokens, skip_special_tokens=True)

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

Aencode

Bpredict

Cdecode

Dfit

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'fit' instead of 'encode' or 'predict'.

Decoding before prediction causes errors.

First encode the text, then predict output tokens, finally decode tokens to text.