B.TechSemester 72024-25Natural Language ProcessingKCS072

Natural Language Processing (KCS072) - AKTU Question Paper 2024-25

B.Tech · Semester 7 · Free PDF Download

This is the official AKTU Natural Language Processing Previous Year Question Paper for B.Tech Semester 7, academic session 2024-25. Published by Dr. A.P.J. Abdul Kalam Technical University (AKTU/UPTU), Lucknow. Free PDF download — no login required.

Course:B.Tech
Semester:Semester 7
Session:2024-25
University:AKTU / UPTU

Rate this paper

Questions Asked in 2024-25

Natural Language Processing (KCS072) — complete question paper · 100 marks · 3 Hours

Section AAttempt all questions in brief. 2 x 10 = 20
  • a
    How does context influence error detection? 1 K 1
  • b
    A Hidden Markov Model (HMM) is u sed for PoS tagging. Explain t he backward algorithms used to compute tag probabilities
  • c
    Provide an example of unification of feature structures for ag reement in number and gender
  • d
    Discuss the limitations of CFGs in modeling natural language syntax. 2 K 1
  • e
    Compare and contrast dictionary -based and distributional metho ds for word similarity measurement
  • f
    Define selectional restrictions. 3 K 2
  • g
    How are speech sounds classified? 4 K 1
  • h
    How do vocal tract shape and size affect the spectrum of speec h sounds? 4 K 1, i. Demonstrate the Viterbi algorithm. 5 K 3, j. Compare and contrast LPC and PLP coefficients for speech featu re extraction
Section BAttempt any three of the following: 10 x 3 = 20
  • a
    Consider the regular expressi on (ab)*c. Draw the corresponding finite- state automaton and explain how it recognizes the language
  • b
    Given the sentence "The dog saw the man with the telescope," illustrate the ambiguity in parsing using dependency grammar. Propose a resolution
  • c
    Discuss how syntax-driven semantic analysis works. Create a semantic attachment for the sentence: "John gave Mary a book."
  • d
    Compare filter-bank and LPC me thods in speech feature extrac tion. Provide numerical examples where possible
  • e
    What are likelihood distortions in speech recognition? Provi de examples and their perceptual impact
Section CAttempt any one part of the following: 10 x 1 = 10
  • a
    A word processor uses a minim um edit distance algorithm to s uggest corrections for misspelled words. If the word "intention" is mi sspelled as "execution," calculate the minimum edit distance and outline t h e alignment steps
  • b
    Compare and contrast interpol ation and backoff smoothing techniques. How are these applied to n-gram models?
  • a
    Discuss the concept of treebanks in NLP. How do they facilit ate training syntactic parsers? Illustrate with an example
  • b
    Explain the CYK parsing algorithm with a worked example of p arsing the sentence "He saw a cat." using a given CFG
  • a
    Given a sentence with multiple possible word senses (e.g., " bank"), outline how Word Sense Disambigua tion (WSD) is performed using supervised learning
  • b
    Implement a bootstrapping method for WSD using a small set o f seed words. Illustrate with examples
  • a
    Explain the mathematical basis of the log-spectral distance measure. Compute it for two spectral frames with given power spectra
  • b
    Derive and explain the LPC coefficients for a given speech f rame. 4 K 1
  • a
    Discuss spectral distortion me asures in speech analysis. Cal culate the cepstral distance for given cepstral coefficients
  • b
    Discuss the role of HMMs in speech recognition. Explain the forward and backward procedures with an example

Question text is extracted from the official AKTU question paper PDF above. Hindi translations are omitted — every question is printed in English in the original paper. Last verified: 2026-08-23.

Syllabus & More PYQs

Paper solve karne se pehle unit-wise syllabus dekh lo