Natural language processing basics in Intro to Computing - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is Natural Language Processing (NLP)?

NLP is a field of computer science that helps computers understand, interpret, and generate human language in a way that is meaningful.

beginner

Name two common tasks in NLP.

Two common NLP tasks are: 1) Text classification, which sorts text into categories, and 2) Sentiment analysis, which finds the feeling or opinion in text.

beginner

What is tokenization in NLP?

Tokenization is the process of breaking text into smaller pieces called tokens, like words or sentences, to make it easier for computers to analyze.

intermediate

Why do we use stop words removal in NLP?

Stop words are common words like 'the', 'is', and 'and' that usually don't add much meaning. Removing them helps focus on important words and speeds up processing.

intermediate

Explain the difference between stemming and lemmatization.

Both reduce words to their base form. Stemming cuts words roughly (e.g., 'running' to 'run'), while lemmatization uses vocabulary and grammar to find the correct base word (e.g., 'better' to 'good').

What does tokenization do in NLP?

A Translates text into another language

B Removes all punctuation from text

C Breaks text into smaller parts like words or sentences

D Counts the number of characters in text

Tokenization splits text into tokens such as words or sentences to help computers analyze language.

Which of these is an example of a stop word?

A and

B computer

C learning

D data

Stop words are common words like 'and' that usually don't add much meaning.

What is the main goal of sentiment analysis?

A To translate text into multiple languages

B To remove stop words from text

C To count the number of words in a sentence

D To find the feeling or opinion expressed in text

Sentiment analysis detects emotions or opinions in text, like positive or negative feelings.

Which process uses grammar and vocabulary to find the base form of a word?

A Lemmatization

B Stemming

C Tokenization

D Stop words removal

Lemmatization uses grammar and vocabulary to find the correct base form of a word.

Why do we remove stop words in NLP?

A To make text longer

B To focus on important words and speed up processing

C To translate text

D To add punctuation

Removing stop words helps focus on meaningful words and makes processing faster.

Describe the main steps involved in preparing text data for NLP tasks.

Think about how we break down and clean text so computers understand it better.

Explain how sentiment analysis can be useful in real life.

Consider how businesses or people might want to know what others think or feel.

Practice

1. What is the main goal of Natural Language Processing (NLP)?

easy

A. To help computers understand and work with human language

B. To create images from text descriptions

C. To speed up computer hardware

D. To encrypt messages for security

Solution

1. Step 1: Understand NLP purpose

   NLP is about making computers understand human language, like English or Spanish.

2. Step 2: Compare options

   Only To help computers understand and work with human language talks about computers working with human language, which matches NLP's goal.

3. Final Answer:

   To help computers understand and work with human language -> Option A

4. Quick Check:

   NLP = computers understand human language [OK]

Hint: NLP = computers + human language understanding [OK]

Common Mistakes:

• Confusing NLP with image processing
• Thinking NLP speeds up hardware
• Mixing NLP with encryption tasks

2. Which of the following is the correct way to split a sentence into words in Python?

easy

A. sentence.add()

B. sentence.split()

C. sentence.remove()

D. sentence.join()

Solution

1. Step 1: Recall Python string methods

   To split a sentence into words, we use the split() method which breaks text at spaces by default.

2. Step 2: Check each option

   Only split() breaks text into parts; join() combines parts, remove() and add() are not string methods.

3. Final Answer:

   sentence.split() -> Option B

4. Quick Check:

   Split = break text into words [OK]

Hint: Use split() to break text into words [OK]

Common Mistakes:

• Using join() instead of split()
• Trying to use remove() on strings
• Confusing add() with string methods

3. What will be the output of this Python code?

text = "I love AI"
tokens = text.split()
print(len(tokens))

medium

A. 1

B. 0

C. 4

D. 3

Solution

1. Step 1: Tokenize the text

   Using split() on "I love AI" splits it into ['I', 'love', 'AI'], which has 3 words.

2. Step 2: Count tokens

   len(tokens) counts the number of items in the list, which is 3.

3. Final Answer:

   3 -> Option D

4. Quick Check:

   Words count = 3 [OK]

Hint: Count words after split() to get token count [OK]

Common Mistakes:

• Counting characters instead of words
• Assuming split() returns a string
• Forgetting split() splits by spaces

4. Find the error in this code snippet for tokenizing text:

text = "Hello world"
tokens = text.split('')
print(tokens)

medium

A. text should be a list, not a string

B. print() is missing parentheses

C. split('') is invalid; split() should have no argument or a space

D. tokens should be joined, not split

Solution

1. Step 1: Check split() argument

   split('') is invalid in Python because empty string is not a valid separator.

2. Step 2: Correct usage

   Use split() with no argument or split(' ') to split by spaces correctly.

3. Final Answer:

   split('') is invalid; split() should have no argument or a space -> Option C

4. Quick Check:

   split('') causes error [OK]

Hint: split('') causes error; use split() or split(' ') [OK]

Common Mistakes:

• Using empty string as split separator
• Thinking print() needs no parentheses in Python 3
• Confusing string and list types

5. You want to count how many times each word appears in a sentence using Python. Which code correctly does this?

hard

A. from collections import Counter
words = sentence.split()
counts = Counter(words)
print(counts)

B. words = sentence.join()
counts = len(words)
print(counts)

C. counts = sentence.count()
print(counts)

D. words = sentence.split('')
counts = dict(words)
print(counts)

Solution

1. Step 1: Tokenize sentence into words

   sentence.split() breaks the sentence into a list of words.

2. Step 2: Use Counter to count words

   Counter(words) counts how many times each word appears and stores results in a dictionary-like object.

3. Step 3: Check other options

   Options A, B, D use wrong methods or syntax for counting words.

4. Final Answer:

   from collections import Counter words = sentence.split() counts = Counter(words) print(counts) -> Option A

5. Quick Check:

   Use Counter + split() for word counts [OK]

Hint: Use Counter with split() to count words fast [OK]

Common Mistakes:

• Using join() instead of split()
• Calling count() without arguments
• Trying to split with empty string