MCQ in Natural Language Processing, Quiz questions with answers in NLP, Top interview questions in NLP with answers
Multiple Choice Questions and Answers in NLP Set - 09
1.
Consider the following simple bigram language model, where the vocabulary
consists of the single word x, and the parameters of the model are;
q(a|*) = 1.0; q(a|a) = 0.4; q(END|a) = 0.6
Which
of the following are the probabilities of the string ‘* a a’ with and without END?
a) 1, 0.4
b) 0.4, 0.24
c) 0.4, 0.6
d) 1.4, 1.0
View Answer
Answer:
(b) 0.4, 0.24
The probability of the
given string can be derived by multiplying appropriate state transition
probabilities.
As per the question,
we need to calculate the following;
P(“* a a”) = P(a|*) *
P(a|a) = 1.0 * 0.4 = 0.4
P(“* a a END”) =
P(a|*) * P(a|a) * P(END|a) = 1.0 * 0.4 * 0.6 = 0.24
|
2. Which of the following measurements are used to evaluate the quality of entity recognition?
a) Precision
b) Recall
c) F-measure
d) All of the above
View Answer
Answer:
(d) All of the above
Entity recognition is
a task of identifying and classifying the entity mentions like person names,
organizations, locations etc. in the text.
The quality of entity
recognition cane be measures using the measurements precision, recall, and
F-measure.
Precision is the
percentage of entities correctly recognized by the underlying system, and can
be measured as follows;
Precision = correctly
recognized/actual recognized
Recall is the percentage
of entities recognized by the underlying system out of all correct entities
with respect to some gold standard dataset.
Recall = correctly
recognized/all correct entities
F-measure is the
harmonic mean of precision and recall
|
3. What is the number of trigrams in a normalized sentence of length n words?
a) n
b) n-1
c) n-2
d) n-3
View Answer
Answer:
(c) n-2
Trigrams are group of
threes words that are written consecutively. Trigrams are extracted by
sliding window of size 3 over the given text.
Number of trigrams in
a document of length n words = n-2 where n>=3.
|
*************
Related links:
- Go to Natural Langugage Processing home page
- Go to NLP - MCQ Quiz Home page
No comments:
Post a Comment