Text preprocessing pipelines in NLP - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the main purpose of a text preprocessing pipeline in NLP?

A text preprocessing pipeline cleans and prepares raw text data into a structured format that machine learning models can understand and learn from effectively.

beginner

Name three common steps in a text preprocessing pipeline.

Common steps include tokenization (splitting text into words), removing stopwords (common words like 'the', 'and'), and stemming or lemmatization (reducing words to their root form).

beginner

Why is tokenization important in text preprocessing?

Tokenization breaks down text into smaller pieces (tokens), usually words or phrases, making it easier for models to analyze and understand the text structure.

intermediate

What is the difference between stemming and lemmatization?

Stemming cuts words to their base form often crudely (e.g., 'running' to 'run'), while lemmatization uses vocabulary and grammar rules to get the correct root word (e.g., 'better' to 'good').

beginner

How does removing stopwords help in text preprocessing?

Removing stopwords eliminates very common words that usually do not add meaningful information, helping models focus on important words and reducing noise.

Which step in text preprocessing splits sentences into individual words?

A Vectorization

B Lemmatization

C Stopword removal

D Tokenization

Tokenization is the process of splitting text into smaller units like words or tokens.

What is the goal of removing stopwords?

A To reduce noise by removing common words

B To convert words to their root form

C To split text into sentences

D To encode text as numbers

Stopword removal eliminates common words that usually do not add useful meaning.

Which technique uses grammar rules to find the base form of a word?

A Stemming

B Lemmatization

C Tokenization

D Stopword removal

Lemmatization uses vocabulary and grammar to find the correct root word.

What is the first step usually done in a text preprocessing pipeline?

A Removing stopwords

B Vectorization

C Tokenization

D Lemmatization

Tokenization is typically the first step to break text into tokens.

Why do we preprocess text before feeding it to a machine learning model?

A To convert text into a format models can understand

B To make text data smaller in size

C To translate text into another language

D To generate new text automatically

Preprocessing converts raw text into structured data suitable for models.

Describe the main steps involved in a text preprocessing pipeline and why each step is important.

Think about how raw text is changed step-by-step to help a model learn.

Explain the difference between stemming and lemmatization with simple examples.

Consider how each method changes words like 'running' or 'better'.