Tutorial (II)
I. Choose the correct one. (1 mark for each)
1. N-Gram language models cannot be used for -------.
A. Spelling Correction B. Predicting the completion of a sentence
C. Removing semantic ambiguity D. Speech Recognition
2. Which of the following is the type of 'walk', 'talk', 'print' ?
A. Regular verb B. Irregular verb C. Complex verb D. Normal
verb
3. Which is used for the ratio of N-gram probability?
A. Frequency B. relative frequency C. cumulative frequency D. both A
&C
4. In an HMM, observation likelihoods measure the likelihood of ________.
A. a POS tag given a word B. a POS tag given the preceding tag
C. a word given a POS tag D. a POS tag given two preceding tags
5. Which is one of supercategories of Parts of speech?
A. Sub class B. Open class C. Join class D. Empty class
II. What is utterance? What kinds of disfluencies are there in the following sentence
explaining briefly each. (3 marks)
III. In NLP, what does Markov assumption mean? (3 marks)
IV. What is part-of-speech tagging? (3 marks)
V. What is the problems of POS tagging? (3 marks)
VI. Write out all the non-zero trigram probabilities from the following mini-corpus of three
sentences. (5 marks)
<s> I am Sam </s>
<s> Sam I am </s>
<s> I do not like green eggs and ham </s>
VII. Discuss the ways to combine morphemes to create words that are common and play
important roles in speech and language processing. (8 marks)