Tokenization in spaCy in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load the spaCy English model.

NLP

import spacy
nlp = spacy.[1]("en_core_web_sm")

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

Aload

Btokenize

Cprocess

Dparse

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'tokenize' or 'parse' instead of 'load' to load the model.

The correct function to load a spaCy model is 'load'.

2fill in blank

medium

Complete the code to create a spaCy Doc object from text.

NLP

doc = nlp([1])

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

Anlp

Bsentence

Ctext

D"This is a sentence."

Attempts:

3 left

💡 Hint

Common Mistakes

Passing a variable name without defining it.

Passing the nlp object itself.

You need to pass a string of text to the nlp object to create a Doc.

3fill in blank

hard

Fix the error in the code to print tokens from the Doc object.

NLP

for token in doc:
    print(token.[1])

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

Astring

Btokens

Ctext

Dword

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'tokens' or 'word' which are not valid token attributes.

The attribute to get the token text is 'text'.

4fill in blank

hard

Fill both blanks to create a list of token texts for tokens longer than 3 characters.

NLP

tokens = [token.[1] for token in doc if len(token.[2]) > 3]

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

Atext

Blemma_

Dpos_

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'lemma_' or 'pos_' which are not strings for length check.

We use 'token.text' to get the token string and check its length.

5fill in blank

hard

Fill all three blanks to create a dictionary of token texts and their part-of-speech tags for tokens longer than 4 characters.

NLP

token_pos = {token.[1]: token.[2] for token in doc if len(token.[3]) > 4}

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

Atext

Bpos_

Dlemma_

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'lemma_' instead of 'pos_' for POS tags.

Checking length on 'pos_' which is not a string.

We use 'text' for keys, 'pos_' for values, and 'text' to check length.