Scribd
Upload
7 views

vnd.openxmlformats-officedocument.wordprocessingml.document&rendition=1

Uploaded by

Anvitha m
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
7 views

vnd.openxmlformats-officedocument.wordprocessingml.document&rendition=1

Uploaded by

Anvitha m
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 5

CSE (AI & ML)

Course code: MR20-1CS0249 Course Name NATURAL LANGUAGE PROCESSING

QUESTION BANK
Q No Question Marks Section Unit
1 Discuss in detail about Natural Language Processing and discuss with 12 Section-I 1
some applications.

2 Calculate the minimum edit distance between two words: “small” and 12 Section-I 1
“smell” using dynamic programming algorithm. Consider cost for
insertion, deletion and substitution is 1, 1, 2.
3 Differentiate non-word and real-word spelling correction? What is 12 Section-I 1
perplexity? Estimate the perplexity of the corpus based on unigram
language model: “the man is a thief but the man is a good man”
4 Find the Maximum Likelihood Estimate and how is it used Language 12 Section-I 1
Model? Given the Corpus

Calculate the following:


a. Find all the possible bigrams from the given corpus.
b. Find frequencies of all the bigrams.
c. Find the frequencies of all unigram.
d. Calculate the Maximum Likelihood Estimate for all bigrams.

5 Discuss about morphology and morphemes. What is bounded and free 12 Section-I 1
morphemes explain with example. What is stemming and how it is
different from lemmatization?
6 Explain about Evaluation of Language Models and Basic Smoothing 12 Section-I 1
7 Explain about Noisy Channel Model for Spelling Correction-Gram 12 Section-I 1
Language Models
8 Develop a comprehensive text processing pipeline that includes 12 Section-I 1
tokenization, stemming, normalization, and spelling correction.
9 Apply different smoothing techniques to a language model and analyze 12 Section-I 1
their impact on performance.
10 Design an algorithm to correct spelling errors in a given text document. 12 Section-I 1
11 Distinguish between inflectional and derivational morphology explains 12 Section-II 2
with example. What is morphological analysis explain with example?
12 Explain in detail about POS tagging with example. 12 Section-II 2
13 What is POS tagging? Find the POS tag for the phrase “the light book”, 12 Section-II 2
using Viterbi algorithm in Hidden markov tagging model with the
following information.

14 Discuss the difference of real words and non-words? What is FSA and 12 Section-II 2
how inflections in words can be represented using FSA, explain with
example.
15 Classifying the problems of Hidden Markov model to predict the POS 12 Section-II 2
tags for a given sentence or phrase? Explain how Baum Welch
algorithm learns the parameters transition matrix, observation matrix
and initial state distribution.
16 State the smoothing in language model. What are the advantages 12 Section-II 2
smoothing? Find the Good turing smoothing for the following
sentence: “he is he is good man”
17 Explain the different categories of affixes in morphology with 12 Section-II 2
examples. What are the differences between content and functional
morphemes? What is the difference between regular and irregular forms
of verbs and nouns respectively?
18 Established why maximum entropy model is better than hidden Markov 12 Section-II 2
model. How POS tagging is achieved in maximum entropy model.
What is beam search explain in detail.
19 How is the uniformity maintained in maximum entropy model? Write 12 Section-II 2
the maximum entropy model principles.
20 Discuss in detail about Conditional Random Fields. 12 Section-II 2
21 Discuss about syntax, parsing and constituency. 12 Section-III 3
22 Differenciate between top down and bottom up parsing. Apply CYK 12 Section-III 3
algorithm to parse the sentence “a pilot likes flying planes” with given
grammar

23 What is inside-outside probability? Apply CYK algorithm to parse the 12 Section-III 3


sentence “a pilot likes flying planes” with given probabilistic context
free grammar to find most probable sparse tree.

24 Explain the dependency parsing and their structure in dependency 12 Section-III 3


parsing with suitable example.

25 Describe dependency graph the main characteristics of dependency 12 Section-III 3


graph. What is the initial value for configuration? Parse the following
sentence with Arc-Eager algorithm.
26 For the given grammar find the inside probabilities for each word for 12 Section-III 3
the following sentence;“Astronomers saw stars with ears”

27 Evaluate the effectiveness of the CKY algorithm in various syntax 12 Section-III 3


parsing tasks.
28 Describe the inside-outside algorithm for calculating probabilities over 12 Section-III 3
parse trees.
29 Explain how PCFGs assign probabilities to different parse trees for a 12 Section-III 3
given sentence.
30 Discuss the evaluation of transition-based parsers using different 12 Section-III 3
metrics.
31 Define distributional semantics. Explain contextual representation and 12 Section-IV 4
how we can learn new words from contextual cues with examples.
32 Explain word space and steps to create words space. Write how it can 12 Section-IV 4
be useful to show the word similarities.
33 How weights can be measured based on context? Deduce the 12 Section-IV 4
formulation for weight measurements. What is difference between
attributional and relational similarity?
34 Explain about one-hot encoding. How words can be represented using 12 Section-IV 4
one-hot encoding explain with example?
35 Define CBOW. How CBOW is used to emebed word explain with 12 Section-IV 4
example.
36 Deliberate the advantages and limitations of distributional semantic 12 Section-IV 4
models compared to other approaches.
37 Discuss the application of distributional semantic models in sentiment 12 Section-IV 4
analysis and topic modeling.
38 Explain the different types of word embedding techniques, including 12 Section-IV 4
word2vec, GloVe, and fastText.
39 Describe the application of word embeddings in various NLP tasks, 12 Section-IV 4
including machine translation, sentiment analysis, and question
answering.
40 Explain how WordNet is used for word sense disambiguation and 12 Section-IV 4
lexical relation extraction.
41 Discuss in detail about text summarization. List the applications of text 12 Section-V 5
summarization give examples.
42 State the main stages of text summarization. How salient words can be 12 Section-V 5
defined? How sentence can be weighted?
43 Explain in detail about how the sentences can be simplified with 12 Section-V 5
example. How summarization systems can be evaluated? What is
ROUGE and how is it used for system evaluation
44 What is text classification? What kind of problems can be solved using 12 Section-V 5
text classification? How text classification problems can be solved?
45 Discuss the different types of text classification tasks, including binary, 12 Section-V 5
multi-class, and hierarchical classification.
46 Explain the evaluation of text classifiers using metrics like accuracy, 12 Section-V 5
precision, recall, and F1-score.
47 Describe the application of sentiment analysis in social media analysis, 12 Section-V 5
product reviews, and customer feedback.
48 Discuss the challenges of sentiment analysis, including handling 12 Section-V 5
sarcasm, irony, and ambiguity.
49 Describe the application of machine learning algorithms like Naive 12 Section-V 5
Bayes, support vector machines (SVMs), and random forests in text
classification.
50 Explain in detail about Sentiment Analysis. 12 Section-V 5

You might also like