Which of the following best describes a Hidden Markov Model (HMM)?<br /> A. a. A generative model <br />B. b. A discriminative model <br />C. c. A deterministic model <br />D. d. A rule-based model
Question
Which of the following best describes a Hidden Markov Model (HMM)?<br /> A. a. A generative model <br />B. b. A discriminative model <br />C. c. A deterministic model <br />D. d. A rule-based model
Solution
A. a. A generative model
Similar Questions
Where does the Hidden Markov Model is used?a) Speech recognitionb) Understanding of real worldc) Both Speech recognition & Understanding of real worldd) None of the mentioned
How does the state of the process is described in HMM?a) Literalb) Single random variablec) Single discrete random variabled) None of the mentioned
HMM: Three Problems• What is the probability of generatingan observation sequence?– Model evaluation• Given observation, what is the mostprobable transition sequence?– Segmentation or path analysis• How do we estimate or optimizethe parameters of an HMM?– Training problem0.6 0.61 30.30.20.2 0.60.320.1 0.1P( )?0.6 0.61 30.30.20.2 0.60.320.1 0.12 2 2 21 32?)|,,,( 21 ==λTxxxXP L)|,(maxarg ),,(*1λXQPQ TqqQ L==))',','('|()),,(|(πλπλ BAXPBAXP =<=
Consider the following sentence: a Markov model tags easilyAssume that based on a HMM, we have the following probabilities: Emission:P1(a|DET) = 0.1, P1(easily|ADV) = 0.1, P1(Markov|N) = 0.1, P1(model|N) = 0.095, P1(model|V) =0.005, P1(tags|N) = 0.080, P1(tags|V) = 0.020,Transition probabilities: P(Y|X) Y DET N V ADJ ADV X DET 0 0.55 0 0.02 0.03 N 0.01 0.1 0.08 0.01 0.02 V 0.16 0.11 0.06 0.08 0.08 ADJ 0.01 0.65 0 0.05 0 ADV 0.08 0.02 0.09 0.04 0.04 Initial probabilitiesP3(DET) = 0.20, P3(N) = 0.06, P3(V) = 0.08, P3(ADV) = 0.07, P3(ADJ) = 0.02.What are the possible tag(s) of the sentence?Assume you want to use the Viterbi algorithm to decode the sentence, write down the expression to be evaluated at the initial step.Write down the expression for the second iteration if the first tag is DET, for a second tag of ADJ
Markov process is a stochastic process in which the future state solely depends on the current state only.Select one:TrueFalse
Upgrade your grade with Knowee
Get personalized homework help. Review tough concepts in more detail, or go deeper into your topic by exploring other relevant questions.