Why NER extracts structured information in NLP - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the library used for Named Entity Recognition (NER).

NLP

import [1]

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

Aspacy

Bnumpy

Cmatplotlib

Dtensorflow

Attempts:

3 left

💡 Hint

Common Mistakes

Importing unrelated libraries like numpy or matplotlib.

Trying to import tensorflow which is for deep learning but not specific to NER.

We use spacy for NER because it provides easy-to-use tools for extracting entities from text.

2fill in blank

medium

Complete the code to load the English language model needed for NER.

NLP

nlp = spacy.load('[1]')

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

Aen_core_web_sm

Bfr_core_news_sm

Ces_core_news_sm

Dde_core_news_sm

Attempts:

3 left

💡 Hint

Common Mistakes

Using models for other languages like French or German.

Forgetting to load a model before processing text.

The English model en_core_web_sm is used to process English text for NER.

3fill in blank

hard

Fix the error in the code to extract entities from the text.

NLP

doc = nlp(text)
for ent in doc.[1]:
    print(ent.text, ent.label_)

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

Aentities

Bents

Ctokens

Dwords

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'entities' which is not a valid attribute in spacy.

Using 'tokens' or 'words' which refer to individual words, not entities.

The correct attribute to get named entities from a processed document is ents.

4fill in blank

hard

Fill both blanks to create a dictionary of entity text and their labels.

NLP

entities = {ent.[1]: ent.[2] for ent in doc.ents}

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

Atext

Blabel_

Cstart_char

Dend_char

Attempts:

3 left

💡 Hint

Common Mistakes

Using character positions instead of text or label.

Mixing up label_ with other attributes.

We use ent.text for the entity string and ent.label_ for its type label.

5fill in blank

hard

Fill all three blanks to filter entities of type 'PERSON' and print their text.

NLP

for ent in doc.ents:
    if ent.[1] == '[2]':
        print(ent.[3])

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

Alabel_

BPERSON

Ctext

Dstart_char

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'label' instead of 'label_' which is the correct attribute.

Printing the wrong attribute like start_char instead of text.

We check if ent.label_ equals 'PERSON' and print ent.text to get the person's name.