NAME OF THE B.

TECH – ARTIFICIAL INTELLIGENCE AND DATA SCIENCE

PROGRAMME
YEAR III
SEMESTER V
REGULATIONS 2022R
COURSE CODE AD3502
COURSE NAME NATURAL LANGUAGE PROCESSING (NLP)

FACULTY NAME (Prepared by) MS. ADITHYA ANIL Contact 9744100439

NAME OF SUBJECT MRS. GOWRI Contact 9600973073
EXPERT(Verified by)

REVISED BLOOMS TAXONOMY(RBT)

L1- Remembering L2 - Understanding L3 - Applying L4 - Analyzing L5 - Evaluating L6 – Creating

Course Objectives:
COSNO Course Objectives
1. To learn the mathematical foundations and basics of Natural Language Processing.
2. To understand the text data processing technologies for processing text data.
3. To understand the role of Information Retrieval and Information Extraction in Text Analytics.
4. To acquire knowledge on text data analytics using language models.
5. To learn about NLP Tools and real-time examples of NLP.

Course Outcomes:
On Completion of the course the students will be able to
CONO Course Outcomes RBT Level
1. Understand the mathematical foundations and basics of Natural L1,L2
Language Processing.
2. Process the text data at the syntactic and semantic level. L3
3. Extract the key information from Text data. L3,L4
4. Analyze the text content to provide predictions related to a specific L4,L5
domain using language models.
5. To design an innovative application using NLP components. L6
 UNIT TITLE
I Introduction to Natural Language Processing

SNO QUESTIONS RBT CO MARK TOPIC IMAGES

Define Natural Language Processing. Definition of

1. L1 CO1 2
NLP
What is Morphological Analysis? Morphological
2. L1 CO1 2
Analysis
List any two mathematical foundations used Mathematical
3. in NLP. L1 CO1 2 Foundations of
NLP

4. What is meant by Tokenization? L1 CO1 2 Tokenization

5. Define Stemming with an example. L1 CO1 2 Stemming

6. What is Lemmatization? L1 CO1 2 Lemmatization

Mention any two applications of boundary Sentence

7. detection. L1 CO1 2 Boundary
Detection
State one difference between morphology Morphology vs
8. L1 CO1 2
and syntax in linguistics. Syntax
Differentiate between stemming and Stemming vs
9. L2 CO1 2
lemmatization. Lemmatization
Explain the purpose of tokenization in NLP. Purpose of
10. L2 CO1 2
Tokenization
Why is morphological analysis important in Importance of
11. NLP? L2 CO1 2 Morphological
Analysis
Describe the significance of linguistic Linguistic
12. background in NLP. L2 CO1 2 Background in
NLP
Illustrate with an example how boundary Boundary
13. determination is useful in sentence L2 CO1 2 Detection –
segmentation. Use Case
How does a stemmer work on different word Stemming –
14. L2 CO1 2
forms? How It Works
15. Interpret the role of NLP in understanding L2 CO1 2 NLP in
human language. Language
 Understanding
Describe the stages involved in Stages of
16. morphological analysis. L2 CO1 2 Morphological
Analysis
Apply stemming to the words: “playing,” Word
17. “played,” “plays.” L3 CO1 2 Stemming –
Application
Identify and tokenize the following sentence: Tokenizing a
18. L3 CO1 2
“NLP enables machines to understand text.” Sentence
Given the word “better,” apply Lemmatization
19. L3 CO1 2
lemmatization and explain the output. Example
Perform morphological analysis on the word Morphological
20. “unhappiness.” L3 CO1 2 Analysis of a
Word
List and briefly explain the components of Components of
21. L1 CO1 6
Natural Language Processing. NLP
Define tokenization, stemming, Tokenization,
lemmatization and give examples for each. Stemming,
22. L1 CO1 8 Lemmatization
– Definitions
and Examples
Describe various types of morphological Types of
23. variations in natural language. L1 CO1 6 Morphological
Variations
Explain the linguistic components relevant to Linguistic
24. Natural Language Processing. L2 CO1 12 Components in
NLP
Discuss the mathematical foundations that Mathematical
25. support NLP techniques. L2 CO1 12 Foundations in
NLP
Describe morphological analysis with Morphological
suitable examples and explain its impact in Analysis –
26. L2 CO1 12
language understanding. Process and
Impact
Differentiate between stemming and Stemming vs
27. lemmatization with examples. L2 CO1 8 Lemmatization
– Differences
Elaborate on the process of tokenization and Tokenization
28. its challenges in NLP. L2 CO1 12 Process and
Challenges
Describe the role of boundary determination Role of
29. in sentence segmentation. L2 CO1 8 Boundary
Determination
 Apply tokenization, stemming, and Text
lemmatization to the sentence: “The children Preprocessing –
30. are playing happily in the garden.” Explain L3 CO1 12 Tokenization,
each step. Stemming,
Lemmatization
Given a paragraph, demonstrate how Sentence
sentence boundary determination can be Boundary
31. L3 CO1 12
applied effectively. Detection –
Application
Given a set of English words, perform full Morphological
32. morphological analysis and interpret the L3 CO1 16 Analysis –
structure. Word Set
Using a sample sentence, illustrate how Morphological
morphological parsing helps in machine Parsing –
33. L3 CO1 12
translation. Machine
Translation
Apply lemmatization to a given dataset and Lemmatization
compare it with stemming. vs Stemming –
34. L3 CO1 8
Dataset
Example
Develop a simple rule-based tokenizer in Rule-Based
35. pseudo-code and explain its logic. L3 CO1 12 Tokenizer –
Pseudocode
Construct a morphological analyzer for Rule-Based
36. words ending with “-ing,” “-ed,” “-s.” L3 CO1 12 Morphological
Analyzer
Apply NLP techniques to normalize noisy Text
37. text input from social media (abbreviations, L3 CO1 12 Normalization
misspellings). – Social Media
Design a small text pipeline including NLP
38. tokenization, stemming, and boundary L3 CO1 16 Preprocessing
determination on real-world text. Pipeline
Analyze the challenges in tokenization due to Tokenization
39. language ambiguities. L4 CO1 12 Challenges –
Ambiguity
Analyze how different stemming algorithms Impact of
40. affect the accuracy of NLP models. L4 CO1 12 Stemming
Algorithms
Discuss the limitations of morphological Morphological
analysis in non-English languages. Analysis
41. L4 CO1 12
Limitations –
Multilingual
42. Analyze and compare rule-based and L4 CO1 12 Rule-Based vs
statistical approaches for sentence boundary Statistical
 detection. Boundary
Detection
Break down the NLP preprocessing pipeline NLP Pipeline
43. L4 CO1 8
and analyze the function of each stage. Breakdown
Evaluate the accuracy of stemming vs Stemming vs
44. lemmatization using precision and recall L4 CO1 16 Lemmatization
metrics. – Evaluation
Evaluate the importance of linguistic Importance of
45. background in designing NLP systems. L5 CO1 12 Linguistic
Background
Critically evaluate the effect of poor Tokenization
46. tokenization on downstream NLP tasks. L5 CO1 12 Impact on NLP
Accuracy
Judge the effectiveness of using stemming Stemming
47. over lemmatization in information retrieval. L5 CO1 8 Effectiveness in
IR
Compare and evaluate boundary detection Boundary
methods based on punctuation vs machine- Detection –
48. L5 CO1 12
learned models. Rule vs ML
Methods
NLP
Propose a hybrid model combining rule- Preprocessing
49. based and machine learning approaches for L6 CO1 16 Pipeline –
improved morphological analysis. Tool-Based
Design
Hybrid Model
Design a mini-NLP pipeline using open-
–
50. source tools to perform preprocessing on a L6 CO1 16
Morphological
sample dataset.
Analysis

UNIT TITLE
II Text Data Analysis
SNO QUESTIONS RBT CO MARK TOPIC IMAGES

1. What is unstructured text data? Unstructured

L1 CO2 2
Data
2. Define Part-of-Speech (POS) tagging. L1 CO2 2 POS Tagging

3. What is the purpose of WordNet? L1 CO2 2 WordNet

4. Define syntactic representation. Syntax

L1 CO2 2
Representation
5. List any two semantic representation Semantic
L1 CO2 2
techniques. Representation
6. What is shallow parsing? Shallow
L1 CO2 2
Parsing
7. What is text similarity? L1 CO2 2 Text Similarity

8. State any two features of syntactic analysis. L1 CO2 2 Syntax

9. Differentiate POS tagging and shallow POS vs

parsing. L2 CO2 2 Shallow
Parsing
10. Explain the role of text similarity in NLP
L2 CO2 2 Text Similarity
applications.
11. How does WordNet contribute to semantic
L2 CO2 2 WordNet
representation?
12. Why is syntactic representation important in
L2 CO2 2 Syntax
text processing?
13. Discuss challenges in representing Unstructured
L2 CO2 2
unstructured text. Data
14. Explain the basic structure of a parse tree. L2 CO2 2 Syntax Tree

15. Describe a use case of POS tagging in NLP. L3 CO2 2 POS Tagging

16. Apply shallow parsing to the sentence: “She Shallow

L3 CO2 2
is singing beautifully.” Parsing
17. Use WordNet to find semantic similarity WordNet
L3 CO2 2
between “car” and “vehicle.” Similarity
18. Tag the sentence “They played cricket
L3 CO2 2 POS Tagging
yesterday” using POS tags.
19. How can text similarity be measured using
L2 CO2 2 Text Similarity
cosine similarity?
20. Illustrate semantic ambiguity with an Semantic
L2 CO2 2
example. Representation
21. Define POS tagging. Explain types of POS
L1 CO2 6 POS Tagging
taggers with examples.
22. What is semantic representation? Describe Semantic
L2 CO2 8
its importance in text understanding. Representation
23. Describe syntactic representation techniques Syntactic
L2 CO2 12
used in NLP. Representation
24. Compare and contrast text similarity
L3 CO2 12 Text Similarity
measures with examples.
25. Explain shallow parsing and its relevance to Shallow
L2 CO2 8
information extraction. Parsing
26. Apply POS tagging, syntactic parsing, and
POS & Syntax
shallow parsing to a paragraph and interpret L3 CO2 12
Parsing
the output.
27. Use semantic representation to disambiguate Word Sense
L3 CO2 12
word senses in the given sentence. Disambiguation
28. Identify and explain syntactic errors in a set Syntax
L4 CO2 12
of sample sentences. Analysis
29. Evaluate the effectiveness of WordNet in
WordNet
improving semantic similarity in information L5 CO2 12
Evaluation
retrieval.
30. Design a component to extract syntactic
Syntax Parsing
features from unstructured documents using L6 CO2 16
System
rule-based parsing.
31. Analyze challenges involved in converting Text
L3 CO2 12
unstructured data into structured form. Structuring
32. Explain the role of text similarity in Text Similarity
L2 CO2 12
recommendation systems with a case study. in IR
33. Build a pipeline for POS tagging, text
NLP Pipeline
similarity and semantic representation using L3 CO2 16
with NLTK
NLTK.
34. Discuss the types of ambiguities in natural Language
L2 CO2 12
language with examples. Ambiguity
35. Apply WordNet-based similarity for WordNet
L3 CO2 12
clustering a group of related terms. Clustering
36. Evaluate the trade-offs between rule-based POS Tagging
L5 CO2 12
and statistical POS tagging methods. Evaluation
37. Apply syntactic parsing on two complex
L3 CO2 12 Syntax Trees
sentences and interpret their parse trees.
38. Analyze why semantic representation is Semantic
L4 CO2 12
necessary in AI-based conversation systems. Representation
39. Design a semantic similarity engine that uses Semantic
WordNet and cosine similarity. L6 CO2 16 Similarity
System
40. Illustrate the usage of shallow parsing for Noun Phrase
L3 CO2 12
identifying noun phrases in English. Chunking
41. Compare syntactic and semantic Syntax vs
L4 CO2 12
representations with suitable examples. Semantics
42. Evaluate challenges and limitations of using WordNet
L5 CO2 12
WordNet for low-resource languages. Limitations
43. Explain different approaches for measuring Similarity
L2 CO2 12
text similarity and their advantages. Measures
44. Apply semantic parsing techniques to extract Intent
L3 CO2 12
intent from a user query. Extraction
45. Analyze the importance of semantic Semantic Role
L4 CO2 12
representation in machine translation. in MT
46. Apply chunking rules to extract verb phrases Verb Phrase
L3 CO2 8
from given sentences. Extraction
47. Compare chunking and full parsing in terms Parsing
of complexity and performance. L5 CO2 12 Methods
Comparison
48. Develop a visualization tool that maps
Dependency
syntactic structure of sentences using L6 CO2 16
Parsing Tool
dependency parsing.
49. Evaluate how semantic analysis enhances the Chatbot
accuracy of chatbots. L5 CO2 12 Semantic
Accuracy
50. Design a rule-based system that performs
Shallow
shallow parsing and tags sentence L6 CO2 16
Parsing Engine
components.

UNIT TITLE
III Information Retrieval and Extraction
SNO QUESTIONS RBT CO MARK TOPIC IMAGES
1. Define Information Retrieval Information
L1 CO3 2
Retrieval
2. What are the key components of an IR IR System
L1 CO3 2
system? Design
3. Define a classical IR model. Classical IR
L1 CO3 2
Model
4. Mention two types of nonclassical IR Nonclassical IR
L1 CO3 2
models. Models
5. Define information extraction. Information
L1 CO3 2
Extraction
6. What is Named Entity Recognition (NER)? Named Entity
L1 CO3 2
Recognition
7. What do you mean by relation identification Relation
L1 CO3 2
in NLP? Identification
8. What is template filling? Template
L1 CO3 2
Filling
9. Differentiate between classical and IR Model
L2 CO3 2
alternative IR models. Comparison
10. Explain how IR models work with ranking
L2 CO3 2 IR Ranking
documents.
11. Discuss the role of NER in information
L2 CO3 2 NER
extraction.
12. Why is relation identification important for Relation
L2 CO3 2
knowledge base construction? Extraction
13. How does template filling support IE Template
L2 CO3 2
systems? Filling
14. Explain the difference between IR and IE. L2 CO3 2 IR vs IE

15. Apply a classical IR model to match a user Classical IR

L3 CO3 2
query with relevant documents. Application
16. Extract entities from the sentence “Tesla was Named Entity
L3 CO3 2
founded by Elon Musk in 2003.” Extraction
17. Identify relation in “Microsoft acquired Relation
L3 CO3 2
LinkedIn in 2016.” Identification
18. Fill a template using the sentence: “Barack Template
L3 CO3 2
Obama was born in Hawaii in 1961.” Filling
19. Given a search query and document list,
L3 CO3 2 IR Ranking
apply ranking to determine relevance.
20. Use a Boolean model to interpret the query: Boolean
L3 CO3 2
“AI AND healthcare.” Retrieval
21. List the key components of an Information IR System
L1 CO3 6
Retrieval system and explain each. Design
22. Describe classical, nonclassical, and IR Models
L2 CO3 12
alternative IR models with examples. Overview
23. Explain the working of a Vector Space Alternative IR
L2 CO3 12
Model in Information Retrieval. Models
24. Compare classical and probabilistic IR
IR Model
models in terms of structure, performance, L4 CO3 12
Analysis
and use cases.
25. Describe the process and applications of Information
L2 CO3 8
Information Extraction. Extraction
26. Apply Boolean and Vector Space Models to IR Model
L3 CO3 12
a given search query and document corpus. Application
27. Extract named entities from a paragraph and
Named Entity
categorize them into person, organization, L3 CO3 12
Recognition
and location.
28. Apply relation identification to the sentence: Relation
L3 CO3 8
“Einstein discovered the theory of relativity.” Extraction
29. Given a set of facts, fill a structured template Template
L3 CO3 12
and explain the steps. Filling
30. Analyze the role of Named Entity
NER and IR
Recognition in improving search engine L4 CO3 12
Integration
performance.
31. Evaluate the effectiveness of classical vs IR Model
L5 CO3 12
modern IR models in web search engines. Evaluation
32. Create an entity-relation template based on a Template
L6 CO3 16
news article of your choice. Design
33. Analyze different template filling methods Template
L4 CO3 12
and discuss their effectiveness. Analysis
34. Evaluate the accuracy of an information
IE Evaluation
extraction system using precision, recall, and L5 CO3 12
Metrics
F1-score.
35. Explain in detail the architecture of an IE IE System
L2 CO3 8
system. Design
36. Apply IE techniques on a real-world job
L3 CO3 12 IE Application
listing to extract structured information.
37. Analyze the advantages of template filling Template Use
L4 CO3 12
over manual data entry in knowledge bases. Case
38. Evaluate the limitations of NER when
NER
applied to informal or noisy text (e.g., L5 CO3 12
Challenges
tweets, chats).
39. Design an IR system that uses a hybrid
Hybrid IR
model combining Boolean and probabilistic L6 CO3 16
System
models.
40. Explain how machine learning improves the ML in Relation
L2 CO3 12
accuracy of relation extraction. Extraction
41. Apply named entity and relation extraction to Knowledge
build a knowledge graph from a news article. L3 CO3 12 Graph from
Text
42. Analyze differences between hard-coded Template
templates and ML-based template filling. L4 CO3 12 Strategy
Comparison
43. Evaluate the performance of two IR models IR Model
L5 CO3 12
on a given dataset. Performance
44. Identify relations and entities in a company
Real-World
acquisition dataset and populate a structured L3 CO3 12
Relation Filling
form.
45. Compare NER tools like SpaCy, NLTK, and
NER Tool
Stanford NLP in terms of speed and L4 CO3 12
Comparison
accuracy.
46. Develop a template filling tool for structured Resume
document generation from unstructured L6 CO3 16 Structuring
resumes. System
47. Create a basic rule-based NER system using Rule-Based
L6 CO3 16
Python and test on sample text. NER Tool
48. Explain how template filling supports Report
L2 CO3 8
automatic report generation. Automation
49. Analyze the trade-offs in using rule-based vs Relation
deep learning models for relation L4 CO3 12 Extraction
identification. Methods
50. Evaluate the ethical concerns and biases in
NER Ethics &
large-scale named entity recognition L5 CO3 12
Bias
systems.

UNIT TITLE
IV Language Modelling
SNO QUESTIONS RBT CO MARK TOPIC IMAGES

1. What is a language model? Language

L1 CO4 2
Models
2. Define probabilistic language models. Probabilistic
L1 CO4 2
Models
3. What is an n-gram model in NLP? N-gram
L1 CO4 2 Language
Model
4. Define Hidden Markov Model. Hidden Markov
L1 CO4 2
Model (HMM)
5. What is topic modeling? Topic
L1 CO4 2
Modeling
6. List any two graph-based models used in
L1 CO4 2 Graph Models
NLP.
7. What is feature selection in text Feature
L1 CO4 2
classification? Selection
8. Define rule-based classifier. Rule-based
L1 CO4 2
Classification
9. What is maximum entropy classification? MaxEnt
L1 CO4 2
Classifier
10. What is clustering in NLP? L1 CO4 2 Clustering

11. Differentiate unigram and bigram models. N-gram Model

L2 CO4 2
Types
12. Explain the limitations of n-gram language N-gram
L2 CO4 2
models. Limitations
13. How does HMM apply to POS tagging? HMM
L2 CO4 2
Application
14. Why is feature selection necessary in Feature
classification tasks? L2 CO4 2 Selection
Importance
15. Compare rule-based and statistical Classifier
L2 CO4 2
classifiers. Comparison
16. Explain the role of topic modeling in Topic
document classification. L2 CO4 2 Modeling in
Classification
17. Apply bigram modeling to the sentence: Bigram
L3 CO4 2
"Natural language processing is fun." Application
18. Use HMM to find the most probable tag
L3 CO4 2 HMM Tagging
sequence for “He eats fish.”
19. Classify a sample text using a rule-based L3 CO4 2 Rule-based
 method. Classification
20. Group the following phrases into clusters:
Phrase-based
["good food", "bad service", "delicious L3 CO4 2
Clustering
meal", "poor taste"]
21. Define and explain language modeling with Language
L1 CO4 6
examples. Modeling
22. Describe the working of n-gram language N-gram
models. L2 CO4 8 Language
Models
23. Explain the architecture and use of Hidden
L2 CO4 12 HMM in NLP
Markov Models in NLP.
24. Compare probabilistic and rule-based Classifier
L4 CO4 12
classifiers with use cases. Analysis
25. Explain topic modeling techniques like LDA LDA / Topic
L2 CO4 12
with real-world examples. Modeling
26. Apply n-gram and HMM models to a given N-gram +
corpus to predict word sequences. L3 CO4 12 HMM
Applications
27. Apply maximum entropy classification to MaxEnt
L3 CO4 12
categorize customer reviews. Application
28. Perform clustering on a given set of
L3 CO4 8 Clustering
words/phrases using K-means.
29. Create a feature vector from a given Feature Vector
L3 CO4 12
document and explain the selection process. Creation
30. Analyze the role of graph-based models in Graph Models
L4 CO4 12
language understanding. in NLP
31. Evaluate the performance of n-gram vs N-gram vs
HMM on a POS tagging task. L5 CO4 12 HMM
Evaluation
32. Design a hybrid model combining rule-based Hybrid
and probabilistic approaches for text L6 CO4 16 Classification
classification. Model
33. Analyze the shortcomings of rule-based Rule-based
L4 CO4 12
systems in language modeling. Limitations
34. Compare word clustering and phrase Clustering
L4 CO4 12
clustering with suitable examples. Analysis
35. Evaluate the benefits of topic modeling in Topic
sentiment analysis of product reviews. L5 CO4 12 Modeling
Evaluation
36. Describe the steps involved in building an n- N-gram Model
L2 CO4 8
gram based language model from scratch. Design
37. Apply a language model to predict the next Trigram
L3 CO4 12
word in a given sentence using a trigram. Prediction
38. Use HMM for speech tagging on a real- HMM POS
L3 CO4 12
world example with calculation steps. Tagging
39. Design a maximum entropy model for spam MaxEnt Spam
detection and explain feature contribution. L6 CO4 16 Detection
System
40. Analyze the effectiveness of clustering in Clustering in
L4 CO4 12
document summarization tasks. Summarization
41. Evaluate performance differences between Feature
feature selection methods (e.g., Chi-square L5 CO4 12 Selection
vs TF-IDF). Evaluation
42. Explain the structure of a graph-based model Graph Model
used in keyword extraction. L2 CO4 8 for Keyword
Extract
43. Apply K-means clustering to organize user Query
L3 CO4 12
queries into categories. Clustering
44. Compare maximum entropy and Naïve Classifier
L4 CO4 12
Bayes classifiers on a sentiment dataset. Comparison
45. Create a simple rule-based classifier for Rule-based
detecting greetings in input text. L6 CO4 16 Classifier
Design
46. Evaluate the trade-offs in using rule-based vs Language
statistical language models in real-time L5 CO4 12 Model
systems. Comparison
47. Discuss the importance of language models Language
in automatic translation systems. L2 CO4 8 Modeling in
Translation
48. Apply word-level and phrase-level clustering Clustering
on a product review dataset. L3 CO4 12 Product
Reviews
49. Analyze how topic modeling enhances Topic
L4 CO4 12
document search and categorization. Modeling in IR
50. Develop an NLP system combining n-gram
and clustering for chatbot response L6 CO4 16 N-gram Model
generation.

UNIT TITLE
V NLP Tools and Applications

SNO QUESTIONS RBT CO MARK TOPIC IMAGES

1. What is NLTK? L1 CO5 2 NLTK

2. Mention two key features of Apache

L1 CO5 2 OpenNLP
OpenNLP.
3. Define text analytics. L1 CO5 2 Text Analytics

4. What is the use of text analytics in social Social Media

L1 CO5 2
media? Analytics
5. List two common NLP applications in life Life Science
L1 CO5 2
sciences. Applications
6. Mention any two NLP applications in legal Legal Text
L1 CO5 2
text processing. Analysis
7. Define text visualization. Text
L1 CO5 2
Visualization
8. What is a word cloud? Visualization
L1 CO5 2
Tools
9. Compare NLTK and OpenNLP in terms of NLTK vs
L2 CO5 2
programming language. OpenNLP
10. Explain the role of NLTK in sentiment NLTK
L2 CO5 2
analysis. Application
11. Describe the use of text mining in legal Legal Text
L2 CO5 2
document processing. Mining
12. What are some challenges in applying NLP Life Science
L2 CO5 2
to biomedical data? Challenges
13. How does OpenNLP perform POS tagging? OpenNLP
L2 CO5 2
Functionality
14. Explain the difference between text analytics Analytics
L2 CO5 2
and data analytics. Types
15. Use NLTK to tokenize the sentence: “NLP is
L3 CO5 2 Tokenization
transforming the world.”
16. Apply OpenNLP to extract named entities Named Entity
L3 CO5 2
from a simple sentence. Extraction
17. Visualize the frequency of words in a Word
paragraph using a basic bar chart. L3 CO5 2 Frequency
Visualization
18. Create a word cloud from a given list of Word Cloud
L3 CO5 2
keywords. Creation
19. Identify the tool you would use for stemming NLTK Tool
L3 CO5 2
and lemmatization. Use
20. Apply OpenNLP for sentence detection from Sentence
L3 CO5 2
a given input text. Detection
21. Define NLTK. List and explain its major NLTK
L1 CO5 6
modules. Overview
22. Describe the architecture and components of OpenNLP
L2 CO5 8
Apache OpenNLP. Architecture
23. Explain the process of sentiment analysis Sentiment
L2 CO5 12
using NLTK. Analysis
24. Compare NLTK and OpenNLP based on Tool
L4 CO5 12
functionality, ease of use, and performance. Comparison
25. Describe how NLP is used for analyzing Social Media
L2 CO5 12
social media data (e.g., tweets, comments). Analysis
26. Apply OpenNLP tools to build a pipeline for POS +
POS tagging and sentence detection. L3 CO5 12 Sentence
Detection
27. Demonstrate the use of NLTK for
Legal Text
preprocessing a legal text (tokenization, L3 CO5 12
Preprocessing
stemming, etc.).
28. Build a basic sentiment classifier for tweets Sentiment
L3 CO5 12
using NLTK or OpenNLP. Classifier
29. Apply text visualization techniques (bar
Social Media
chart, word cloud) to summarize social L3 CO5 8
Visualization
media posts.
30. Analyze the impact of NLP in transforming NLP in
L4 CO5 12
healthcare data into structured form. Healthcare
31. Evaluate the effectiveness of OpenNLP in
OpenNLP in
extracting information from legal case L5 CO5 12
Legal Domain
summaries.
32. Design a dashboard to visualize NLP outputs NLP
from NLTK pipelines. L6 CO5 16 Dashboard
Design
33. Analyze the differences between Text
visualization tools used in text analytics. L4 CO5 12 Visualization
Tools
34. Evaluate the role of text analytics in
Text Analytics
enhancing decision-making in biomedical L5 CO5 12
in Life Science
research.
35. Describe the end-to-end process of applying Customer
NLP tools to analyze customer feedback on L2 CO5 8 Feedback
social platforms. Analysis
36. Apply both NLTK and OpenNLP to the Cross Tool
L3 CO5 12
same text and compare the output. Analysis
37. Design a pipeline using NLTK for extracting Resume Parser
L6 CO5 16
named entities from resumes. Design
38. Evaluate how NLP helps in automating legal Legal
document classification. L5 CO5 12 Document
Automation
39. Apply NLTK to visualize common terms in a Word
collection of articles using matplotlib. L3 CO5 12 Frequency
Visualization
40. Compare case studies of NLP usage in legal Cross-domain
L4 CO5 12
vs life science domains. Case Studies
41. Discuss case studies that showcase OpenNLP Case
L2 CO5 12
OpenNLP in real-world applications. Studies
42. Build a text summarizer tool using NLTK Text
and visualize key sentences. L6 CO5 16 Summarizer
Design
43. Analyze the ethical implications of text Ethics in Social
L4 CO5 12
analytics in social media monitoring. Media NLP
44. Apply NLTK and Matplotlib to generate Sentiment
L3 CO5 12
sentiment plots for a product review dataset. Visualization
45. Evaluate OpenNLP’s performance in named
NER
entity recognition using precision and recall L5 CO5 12
Evaluation
metrics.
46. Explain text analytics workflow with an Text Analytics
L2 CO5 8
example from the healthcare domain. Workflow
47. Apply topic modeling (e.g., using LDA) with Topic
NLTK on a legal document corpus. L3 CO5 12 Modeling in
Legal Text
48. Discuss the advantages of using text
Biomedical
visualization in summarizing biomedical L4 CO5 12
Visualization
papers.
49. Create a tool using NLTK to detect abusive Abuse
L6 CO5 16
comments in social media platforms. Detection Tool
50. Evaluate the impact of NLP-based text
NLP in Public
analytics in improving public health L5 CO5 12
Health
surveillance.