Đề Thi PE NLP301c - SP26 - NO2 - PE - RE

[adminadmin is verified member.]

Học kỳ

SP2026

Thời Gian

3/5/26

Loại tài liệu

PE

NLP301c SP26 NO2 PE RE

NLP301c PE INSTRUCTIONS​

Student preparation:

• Before proceeding, install Python 3.8 or higher.
  
  
  
  
• Install NLTK (nltk-3.6.2), downloadable from
  You do not have permission to view link Đăng nhập hoặc Đăng ký.
  
  
  
  
  
  
  
• Run cmd with administrator role, change the current path in prompt to the nltk-3.6.2 folder, and type the following command to set up: python setup.py install
  
  
  
  
  
  
• Once installed, start up the Python interpreter and install the data required for the book by typing:
  
  
  
  
  Python
  
  <span>&gt;&gt;&gt; </span><span>import</span> nltk<br><span>&gt;&gt;&gt; </span>nltk.download()<br>
• In the NLTK Downloader, select the 'book' collection and ensure it is fully installed.
  
  
  

---

Instructions for completing PE:​

• For submission: Create a folder named in the format: YourName YourRollNumber NLP301c
  
  
  
  
  
  
• Example: Nguyễn Thế Hùng with roll number SE09234 will submit: HungNT SE09234 NLP301c
  
  
  
  
  
  
• Create separate files named Q1.py, Q2.py, Q3.py, Q4.py and place them in the folder.
  
  
  
  
• Submit the folder to the server. Incorrect submissions will receive a ZERO.
  
  
  
  
  

---

Question 1: (2 marks)​

• Task: Write a program to count how many words in a customer feedback contain all lowercase letters only.
  
  
  
  
• Input: A string containing the feedback text.
  
  
  
  
• Desired Output: An integer representing the number of words written entirely in lowercase.
  
  
  
  
• Example:
  
  • Input: "This product is amazing and works Perfectly."
  • Output: 5
    
    
    
    
    

Question 2: (2 marks)​

• Task: Write a program to remove all consecutive duplicate characters from a chatbot message.
  
  
  
  
• Requirements:
  
  • Case-sensitive.
    
    
    
    
  • Only remove consecutive duplicates (not all duplicates).
    
    
    
• Input: A string containing chatbot text.
  
  
  
  
• Desired Output: A cleaned string.
  
  
  
  
• Example:
  
  • Input: "heyyy!!! I loooove NLP"
  • Output: "hey! I love NLP"
    
    
    
    
    

Question 3: (3 marks)​

• Task: Write a program to extract all valid job titles from a recruitment post.
  
  
  
  
• A valid job title must meet these criteria:
  
  1. Starts with an uppercase letter.
     
     
     
     
  2. Contains only letters and spaces.
     
     
     
     
  3. Must be at least 2 words long.
     
     
     
• Input: A string containing a job posting.
  
  
  
  
• Desired Output: A list of job titles in order of appearance.
  
  
  
  
• Example:
  
  • Input: "We are hiring Data Scientist and Software Engineer. Join our team as a Junior Developer!"
  • Output: ['Data Scientist', 'Software Engineer', 'Junior Developer']
    
    
    
    
    

Question 4: (3 marks)​

• Task: Write a program to process social media captions and return the longest word in each sentence.
  
  
  
  
• Rules:
  
  1. Sentences are separated by ., !, ?
     
     
     
     
     
     
  2. Ignore punctuation.
     
     
     
     
  3. If multiple longest words exist, return the first one.
     
     
     
• Input: A paragraph string.
  
  
  
  
• Desired Output: A list of longest words (one per sentence).
  
  
  
  
• Example:
  
  • Input: "AI is transforming industries. NLP is very powerful!"
  • Output: ['transforming', 'powerful']