Problem 1: Viterbi Decoding VB NN VB State Transition Probabilities (A array) PRP PRPS JJ 0.15 0.5 0.2 0.05 0.05 VB 0.0001 0.2 0.005 0.004 0.002 NN 0.01 0.05 0.002 0.002 0.001 PRP 0.25 0.05 0.001 0.001 0.01 PRPS 0.25 0.1 0.001 0.001 0.05 JJ 0.0001 0.05 0.001 0.05 Observation Likelihoods (B array) Dumbledore fed his phoenix peanuts 0 0.10 0 0 0 0 0 0.2 0.10 0.1 0.15 0 0 0.10 0 0 0 0 0 0.05 0 NN PRP PRPS JJ 0 0 0 0 0.2 (a) Using the matrices given, compute by hand the Viterbi trellis (as shown in Figures 6.10 and 6.12) and backpointer matrix (as used in Figure 6.11) for the sentence "Dumbledore fed his phoenix peanuts". (b) What is the most likely sequence of tags? Problem 1: Viterbi Decoding VB NN VB State Transition Probabilities (A array) PRP PRPS JJ 0.15 0.5 0.2 0.05 0.05 VB 0.0001 0.2 0.005 0.004 0.002 NN 0.01 0.05 0.002 0.002 0.001 PRP 0.25 0.05 0.001 0.001 0.01 PRPS 0.25 0.1 0.001 0.001 0.05 JJ 0.0001 0.05 0.001 0.05 Observation Likelihoods (B array) Dumbledore fed his phoenix peanuts 0 0.10 0 0 0 0 0 0.2 0.10 0.1 0.15 0 0 0.10 0 0 0 0 0 0.05 0 NN PRP PRPS JJ 0 0 0 0 0.2 (a) Using the matrices given, compute by hand the Viterbi trellis (as shown in Figures 6.10 and 6.12) and backpointer matrix (as used in Figure 6.11) for the sentence "Dumbledore fed his phoenix peanuts". (b) What is the most likely sequence of tags