Natural Language Processing
CSE · Quiz · Fall 25
Read the questions as text
Read off the PDF by AI, so it may have mistakes. The PDF is the original.
Daffodil International University
Department of Computer Science and Engineering
Faculty of Science & Information Technology
Time: 50 min
Quiz-2
Semester: Fall 2025
Course Code: CSE445
Course Title: Natural Language Processing
1. Consider the corpus:
D1: "data data science is fun";
D2: "science is fun fun";
D3: "data science is boring";
D4: "data data data is science";
D5: "fun is fun".
(a) Compute term frequencies for each document and inverse document frequencies for the corpus vocabulary.
(b) Compute the TF-IDF vector of each document.
(c) Identify the most informative term(s) in each document. [7.5]
2. The film "Jawan" released in 2024. The following training set contains reviews with labels. Apply Laplace smoothing with alpha = 1. [7.5]
Review | Label
Jawan is great great | Good
Jawan is bad | Bad
Jawan is average | Neutral
great movie | Good
boring and bad | Bad
average is average | Neutral
A new review appears: "Jawan is not a great movie". Determine the predicted label. Show the full calculation steps.