First NLP pipeline - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the first step in a typical NLP pipeline?

The first step is usually text preprocessing, which includes cleaning the text by removing unwanted characters, converting text to lowercase, and tokenizing sentences into words.

beginner

What does tokenization mean in NLP?

Tokenization means splitting text into smaller pieces called tokens, usually words or sentences, to make it easier for the computer to understand and analyze the text.

beginner

Why do we remove stop words in an NLP pipeline?

Stop words are common words like 'the', 'is', and 'and' that usually do not add much meaning. Removing them helps the model focus on important words and improves efficiency.

intermediate

What is lemmatization in an NLP pipeline?

Lemmatization is the process of converting words to their base or dictionary form, like changing 'running' to 'run', to treat different forms of a word as the same.

intermediate

Name the main components of a simple NLP pipeline.

A simple NLP pipeline usually includes:

• Text preprocessing (cleaning, tokenization)
• Stop word removal
• Lemmatization or stemming
• Feature extraction (like bag of words or embeddings)
• Model training or prediction

What is the purpose of tokenization in an NLP pipeline?

A Convert text to uppercase

B Remove punctuation from text

C Split text into smaller units like words or sentences

D Train the machine learning model

Tokenization breaks text into smaller pieces called tokens, which helps the computer analyze the text.

Which step removes common words like 'and', 'the', and 'is'?

A Stop word removal

B Lemmatization

C Tokenization

D Feature extraction

Stop word removal filters out common words that usually do not add meaning.

What does lemmatization do in an NLP pipeline?

A Splits text into sentences

B Converts words to their base form

C Removes punctuation

D Counts word frequency

Lemmatization converts words like 'running' to 'run' to unify word forms.

Which of these is NOT usually part of the first NLP pipeline steps?

A Text cleaning

B Tokenization

C Stop word removal

D Model training

Model training usually comes after preprocessing steps like cleaning and tokenization.

Why do we preprocess text in NLP?

A To prepare text for analysis by cleaning and structuring it

B To make text harder to understand

C To add random noise to data

D To translate text into another language

Preprocessing cleans and structures text so models can analyze it better.

Describe the main steps involved in a first NLP pipeline and why each step is important.

Think about how raw text is prepared for a computer to understand.

Explain how tokenization and lemmatization help improve text analysis in NLP.

Consider how breaking down and simplifying words helps machines.

Practice

1. What is the main purpose of an NLP pipeline in machine learning?

easy

A. To translate text into different languages automatically

B. To store large amounts of text data

C. To process text step-by-step for making predictions

D. To create images from text

Solution

1. Step 1: Understand the role of an NLP pipeline

   An NLP pipeline breaks down text processing into steps like cleaning, vectorizing, and modeling.

2. Step 2: Identify the goal of these steps

   The goal is to prepare text data so a model can make predictions, such as classifying or understanding text.

3. Final Answer:

   To process text step-by-step for making predictions -> Option C

4. Quick Check:

   NLP pipeline = step-by-step text processing for predictions [OK]

Hint: Remember: pipeline means step-by-step processing [OK]

Common Mistakes:

• Thinking pipeline stores data only
• Confusing pipeline with translation tools
• Assuming pipeline creates images

2. Which of the following is the correct way to import a text vectorizer from scikit-learn for an NLP pipeline?

easy

A. import CountVectorizer from sklearn.text

B. from sklearn.feature_extraction.text import CountVectorizer

C. from sklearn.vectorizer import TextCount

D. import text_vectorizer from sklearn.feature

Solution

1. Step 1: Recall the correct module for text vectorizers

   Scikit-learn provides CountVectorizer in the feature_extraction.text module.

2. Step 2: Check the import syntax

   The correct syntax is: from sklearn.feature_extraction.text import CountVectorizer.

3. Final Answer:

   from sklearn.feature_extraction.text import CountVectorizer -> Option B

4. Quick Check:

   Correct import = from sklearn.feature_extraction.text import CountVectorizer [OK]

Hint: Remember: CountVectorizer is in feature_extraction.text [OK]

Common Mistakes:

• Using wrong module names
• Incorrect import syntax
• Confusing class names

3. Given the following code snippet, what will be the output of print(X.toarray())?

from sklearn.feature_extraction.text import CountVectorizer
texts = ['cat and dog', 'dog and mouse']
vectorizer = CountVectorizer()
X = vectorizer.fit_transform(texts)
print(X.toarray())

medium

A. [[1 1 1 0]
[1 0 1 1]]

B. [[1 0 1 1]
[1 1 0 1]]

C. [[1 1 0 1]
[1 0 1 1]]

D. [[0 1 1 1]
[1 1 1 0]]

Solution

1. Step 1: Identify the vocabulary from the texts

   The texts are 'cat and dog' and 'dog and mouse'. The unique words are: 'and', 'cat', 'dog', 'mouse'. CountVectorizer sorts them alphabetically: ['and', 'cat', 'dog', 'mouse'].

2. Step 2: Map each text to counts of these words

   First text: 'cat and dog' -> counts: and=1, cat=1, dog=1, mouse=0 -> [1 1 1 0]. Second text: 'dog and mouse' -> counts: and=1, cat=0, dog=1, mouse=1 -> [1 0 1 1].

3. Final Answer:

   [[1 1 1 0] [1 0 1 1]] -> Option A

4. Quick Check:

   Vocabulary order and counts match [[1 1 1 0] [1 0 1 1]] [OK]

Hint: Remember: CountVectorizer sorts words alphabetically [OK]

Common Mistakes:

• Mixing word order in output
• Confusing counts of words
• Assuming different vocabulary order

4. You wrote this code but get an error: AttributeError: 'CountVectorizer' object has no attribute 'transform_text'. What is the likely fix?

from sklearn.feature_extraction.text import CountVectorizer
vectorizer = CountVectorizer()
vectorizer.transform_text(['hello world'])

medium

A. Replace transform_text with transform

B. Import CountVectorizer from a different module

C. Call fit before transform_text

D. Use fit_transform_text instead

Solution

1. Step 1: Identify the incorrect method name

   The error says 'CountVectorizer' has no method 'transform_text'. The correct method is 'transform'.

2. Step 2: Correct the method call

   Replace transform_text with transform to fix the error.

3. Final Answer:

   Replace transform_text with transform -> Option A

4. Quick Check:

   Correct method name is transform [OK]

Hint: Check method names carefully in docs [OK]

Common Mistakes:

• Using non-existent method names
• Not reading error messages
• Trying to call fit_transform_text which doesn't exist

5. You want to build a simple NLP pipeline that converts text to numbers and then trains a logistic regression model to classify text. Which sequence of steps is correct?

hard

A. Predict on new text -> Vectorize text -> Train logistic regression

B. Train logistic regression -> Vectorize text -> Predict on new text

C. Vectorize text -> Predict on new text -> Train logistic regression

D. Vectorize text -> Train logistic regression -> Predict on new text

Solution

1. Step 1: Understand the pipeline order

   First, text must be converted to numbers using vectorization before training a model.

2. Step 2: Follow logical flow

   After vectorizing, train the logistic regression model, then use it to predict on new vectorized text.

3. Final Answer:

   Vectorize text -> Train logistic regression -> Predict on new text -> Option D

4. Quick Check:

   Correct pipeline order = Vectorize text -> Train logistic regression -> Predict on new text [OK]

Hint: Always vectorize before training or predicting [OK]

Common Mistakes:

• Trying to train before vectorizing
• Predicting before training
• Skipping vectorization step