Information extraction patterns in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to extract named entities from text using spaCy.

NLP

import spacy
nlp = spacy.load('en_core_web_sm')
doc = nlp('Apple is looking at buying U.K. startup for $1 billion')
for ent in doc.[1]:
    print(ent.text, ent.label_)

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

Aentities

Bents

Ctokens

Dspans

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'entities' instead of 'ents' causes an AttributeError.

Trying to iterate over 'tokens' instead of entities.

The correct attribute to access named entities in a spaCy Doc object is 'ents'.

2fill in blank

medium

Complete the code to extract all email addresses from a text using a regular expression.

NLP

import re
text = 'Contact us at [e-mail] or [e-mail]'
emails = re.findall(r'[1]', text)
print(emails)

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

A\b\w+\b

B\d{3}-\d{2}-\d{4}

C[\w\.-]+@[\w\.-]+\.[a-zA-Z]{2,6}

Dhttps?://[\w\.-]+

Attempts:

3 left

💡 Hint

Common Mistakes

Using regex for phone numbers or URLs instead of emails.

Missing escape characters in regex.

The regex '[\w\.-]+@[\w\.-]+\.[a-zA-Z]{2,6}' matches typical email addresses.

3fill in blank

hard

Fix the error in the code to extract dates from text using spaCy's Matcher.

NLP

from spacy.matcher import Matcher
import spacy
nlp = spacy.load('en_core_web_sm')
matcher = Matcher(nlp.vocab)
pattern = [{'ENT_TYPE': '[1]'}]
matcher.add('DATE_PATTERN', [pattern])
doc = nlp('We met on January 10th, 2023.')
matches = matcher(doc)
for match_id, start, end in matches:
    span = doc[start:end]
    print(span.text)

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

ADATE

BTIME

CPERSON

DORG

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'TIME' or other entity types that do not match dates.

Not using the correct key 'ENT_TYPE' in the pattern.

The entity type for dates in spaCy is 'DATE'.

4fill in blank

hard

Fill both blanks to create a dictionary of word frequencies from a text.

NLP

text = 'apple banana apple orange banana apple'
words = text.split()
freq = {word: [1] for word in words if words.count(word) [2] 1}
print(freq)

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

Awords.count(word)

Bwords.index(word)

C>

D==

Attempts:

3 left

💡 Hint

Common Mistakes

Using index instead of count for frequency.

Using '==' instead of '>' to filter words.

We count occurrences of each word and keep only those with count greater than 1.

5fill in blank

hard

Fill all three blanks to extract entities and their labels into a dictionary using spaCy.

NLP

import spacy
nlp = spacy.load('en_core_web_sm')
doc = nlp('Google was founded in September 1998 by Larry Page and Sergey Brin.')
entities = [1]
for ent in doc.ents:
    entities[ent.[2]] = ent.[3]
print(entities)

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

A{}

Btext

Clabel_

Dlist

Attempts:

3 left

💡 Hint

Common Mistakes

Using list instead of dictionary for entities.

Using ent.label instead of ent.label_.

We create an empty dictionary {}, then use ent.text as key and ent.label_ as value.