Question Paper 1: Natural Language Processing (DLOC – III)
Paper / Subject Code: 42213 / Natural Language Processing (DLOC – III)
Time: 3 hours
Max. Marks: 80
N.B.:
- Question No. 1 is compulsory.
- Assume suitable data if necessary.
- Attempt any three questions from the remaining questions.
Q1. Solve any Four out of Five (20 marks)
a. What is Natural language processing? Explain ambiguity in natural languages with suitable examples.
b. Explain in brief inflectional and derivational morphology with suitable examples.
c. What is semantic analysis? Discuss different semantic relationships between the words.
d. What is Named-Entity recognition? Define its types.
e. What is rule-based machine translation?
Q2. (10 marks each)
a. What is POS tagging? List different approaches to POS tagging. Explain any one approach in brief.
b. Discuss various stages involved in the NLP process with suitable examples.
Q3. (10 marks each)
a. Explain with suitable examples the following relationships between word meanings: Homonymy, Polysemy, Synonymy, Hyponymy, Hypernymy.
b. Consider the following corpus:
<s> She says not to wait patiently <\s>
<s> He says we need to help him <\s>
<s> They asked us to arrive early <\s>
List all possible bigrams. Compute conditional probabilities and predict the next word for the word “do”.
Q4. (10 marks each)
a. What is Word Sense Disambiguation? Explain dictionary-based approach to Word Sense Disambiguation.
b. Explain Hobbs algorithm for pronoun resolution.
Q5. (10 marks each)
a. Explain edit distance algorithm with an example. Show working of the minimum number of operations required to transform “kitten” into “sitting”.
b. Explain Hidden Markov Model with example.
Q6. Write a note on any 2 (10 marks each)
- Information Retrieval
- Wordnet
- Syntactic and Semantic Constraints on Coreference
- Sentiment Analysis
Question Paper 2: Natural Language Processing (DLOC – III)
Paper / Subject Code: 42213 / Natural Language Processing (DLOC – III)
Time: 3 hours
Total Marks: 80
N.B.:
- Question No. 1 is compulsory.
- Attempt any three questions from the remaining five questions.
- Assume suitable data if necessary and justify the assumptions.
- Figures to the right indicate full marks.
Q1. Answer the Following (20 marks)
a. Compare derivational and inflectional morphology with suitable examples.
b. Discuss various challenges in processing natural language.
c. Discuss Information Retrieval vs Information Extraction in detail.
d. What do you mean by word sense disambiguation (WSD)? Explain machine learning-based (Naive Bayes) approach for WSD.
Q2. (10 marks each)
a. Write a note on Syntactic and Semantic Constraints on Coreference.
b. Explain Porter’s Stemming algorithm with an example.
Q3. (10 marks each)
a. Explain with suitable examples the following relationships between word meanings: Homonymy, Polysemy, Synonymy, Antonymy, Hypernymy, Hyponymy, Meronomy.
b. What is Natural Language Processing (NLP)? Discuss various stages involved in the NLP process with suitable examples.
Q4. (10 marks each)
a. Explain N-gram model with example.
b. Explain in detail Stochastic (HMM) tagging.
Q5. (10 marks each)
a. Consider the following Training data:
<s> I am Sam <\s>
<s> Sam I am <\s>
<s> Sam I like <\s>
<s> Sam I do like <\s>
<s> do I like Sam <\s>
Assume that we use a bigram language model based on the above training data. What is the most probable next word predicted by the model for the following word sequences?
1. <s> Sam ...
2. <s> Sam I do ...
3. <s> Sam I am Sam ...
4. <s> do I like ...b. What is parsing? Explain types of parsing in NLP.
Q6. Write Short Notes (5 marks each)
a. Named Entity Recognition
b. Wordnet
c. Reference Resolution Problem
d. Machine Translation
