Lemmatization in spaCy in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load the English model in spaCy.

NLP

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

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

Aload

Bparse

Cinstall

Ddownload

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'download' instead of 'load' to get the model.

Trying to 'install' the model inside the code instead of loading it.

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

2fill in blank

medium

Complete the code to process the text with the loaded spaCy model.

NLP

doc = nlp([1])

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

Adoc

Bnlp

Cspacy

D"This is a test sentence."

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the model object 'nlp' instead of a text string.

Passing an unprocessed variable instead of a string.

You need to pass a string of text to the model to process it.

3fill in blank

hard

Fix the error in the code to get the lemma of each token.

NLP

lemmas = [token.[1] for token in doc]

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

Alemmatize

Blemma_

Clemma

Dtext

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'lemma' without underscore which returns a token attribute object.

Trying to call a method 'lemmatize' which does not exist.

The correct attribute to get the lemma string is 'lemma_'.

4fill in blank

hard

Fill both blanks to create a dictionary of tokens and their lemmas.

NLP

lemma_dict = [1]([2]: token.[3] for token in doc)

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

Adict

Blist

Clemma_

Dset

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'list' or 'set' instead of 'dict' to create the dictionary.

Using 'lemma' without underscore for the lemma attribute.

Use 'dict' to create a dictionary, 'token.text' for keys, and 'lemma_' to get lemma strings.

5fill in blank

hard

Fill all three blanks to print each token and its lemma in a loop.

NLP

for token in doc:
    print(token.[1], token.[2], token.[3])

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

Atext

Blemma_

Cpos_

Dtag_

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'lemma' or 'pos' without underscore which are not strings.

Mixing up 'tag_' and 'pos_' which represent different tag types.

Print token text, lemma string, and part-of-speech tag string.