Part-Of-Speech tagging (POS) — past-year questions
Natural Language Processing (CSDC7013) · Semester 7 · Module 3 · Comps
17 past-year questions on Part-Of-Speech tagging (POS) have appeared in Mumbai University CSDC7013 papers between 2024–2026, 21 times in total. Every question is shown in full below with its marks and repeat count. Model answers require a free account.
Questions asked on Part-Of-Speech tagging (POS)
- 1.
Explain Shift Reduce Parser in NLP with example.
5M2× seenlast asked 2026 - 2.
For a given grammar using CYK or CKY algorithm parse the statement "The man read this book" Rules: S -> NP VP S -> Aux NP VP S -> VP NP -> Det NOM NOM -> Noun NOM -> Noun NOM VP -> Verb VP -> Verb NP Det -> that | this | a | the Noun -> book | flight | meal | man Verb -> book | include | read Aux -> does
10M2× seenlast asked 2026 - 3.
Explain hidden Markov model for POS based tagging.
10M2× seenlast asked 2025 - 4.
What are the limitations of Hidden Markov Model (HMM) and MaxEnt Model for POS Tagging.
5M2× seenlast asked 2025 - 5.
Compare rule-based, stochastic and transformation-based POS tagging.
5M1× seenlast asked 2026 - 6.
Consider the following corpus: <s> the/DT teacher/NN explains/V the/DT lesson/NN </s> <s> the/DT student/NN reads/V a/DT book/NN </s> <s> teacher/NN guides/V student/NN </s> Compute the emission and transition probabilities for a bigram HMM. Also decode the following sentence using Viterbi algorithm. "The student reads the book"
10M1× seenlast asked 2026 - 7.
Explain Limitations of Hidden Markov Model (HMM) and MaxEnt Model for POS Tagging.
5M1× seenlast asked 2026 - 8.
Explain use of Probabilistic Context Free Grammar (PCFG) in NLP.
10M1× seenlast asked 2025 - 9.
Define POS Tagging. Explain why it is a necessary pre-processing step for higher-level NLP tasks like Named Entity Recognition (NER). Using the common Penn Treebank tagset, assign the appropriate POS tag to each word in the following sentence. "The fast "train" from "Dadar" "will" arrive at platform "seven" shortly." Briefly explain the reasoning for the tag assigned to the highlighted words.
10M1× seenlast asked 2025 - 10.
Consider the following corpus for POS tagging: <S> Martin Justin can watch Will <E> <S> Spot will watch Martin <E> <S> Will Justin spot Martin <E> <S> Martin will pat Spot <E> For the given above corpus, S indicates start of the statement and E indicates end of the statement. N: Noun [Martin, Justin, Will, Spot, Pat] M: Modal verb [can, will] V: Verb [watch, spot, pat] Create Transition Matrix & Emission Probability Matrix. Statement is "Justin will spot Will" Apply Hidden Markov Model and do POS tagging for the given statement.
10M1× seenlast asked 2025 - 11.
How conditional random fields (CRF) are used for sequence labelling task.
10M1× seenlast asked 2025 - 12.
Discuss the challenges in part of speech tagging.
5M1× seenlast asked 2024 - 13.
What is hybrid POS tagging?
5M1× seenlast asked 2024 - 14.
Explain how Maximum Entropy is used for sequence labeling.
10M1× seenlast asked 2024 - 15.
Consider the following corpus: <s> a/DT dog/NN chases/V a/DT cat/NN </s> <s> the/DT dog/NN barks/V loudly/RB </s> <s> a/DT cat/NN runs/V fast/RB </s> Compute the emission and transition probabilities for a bigram HMM. Also, decode the following sentence using the Viterbi algorithm. The cat chases the dog.
10M1× seenlast asked 2024 - 16.
Demonstrate the concept of conditional Random field in NLP.
10M1× seenlast asked 2024 - 17.
Construct a parse tree for the following sentence using the given CFG rules: The tall girl sings. Rules: S -> NP VP NP -> Det Adj N | Det N VP -> V | V NP Det -> "the" Adj -> "tall" N -> "girl" V -> "sings"
10M1× seenlast asked 2024
Want the answers to these questions?
The questions above are free to read. Create a free account to get AI model answers for Natural Language Processing, a curated set of the questions that matter most, flashcard revision, and a study plan built around your exam date.