stathwang / pos-taggers Goto Github PK

Thanks for your very well tutorial, Suppose the word like " I need 100 dollar to buy a iphone ..
.......What is the part-of-speech tags are abbreviation of 100 ?
Also like 2nd example :" My account is number is ABC123XT
What is the part-of-speech tags are abbreviation of ABC123XT ?

Can you please help me out how to implement on your code?

Also, can you please give node what is the execution steps ?

I get error while running below model

(base) C:\Users\nbehera4\Desktop\AI\POS-Taggers\model>python pos.py

Traceback (most recent call last):
File "pos.py", line 315, in
main()
File "pos.py", line 277, in main
unigram_p, bigram_p, trigram_p, trigram_d = calc_ngram_probs(brown_tags, unigram_c, bigram_c, trigram_c)
File "pos.py", line 82, in calc_ngram_probs
unigram_p = {(a,): math.log(unigram_c[(a,)], 2) - math.log(unigram_total, 2) for a in unigram_c}
File "pos.py", line 82, in
unigram_p = {(a,): math.log(unigram_c[(a,)], 2) - math.log(unigram_total, 2) for a in unigram_c}
ValueError: math domain error

Hi Seong Hyun, I've been able to implement a majority of this repository, albeit, in a different way. I've been able to calculate the log probabilities of both the transmissions and emissions of my training corpus. However, it seems like your implementation of the viterbi algorithm is not working. Do you know why that could be? Do you happen to have a fix for this? I'm trying to work on one, but I haven't been able to come up with a solution no matter what I try. It doesn't seem like you've been active on github recently, but it would be great if you could get back to me on this soon. It would be very much appreciated. Thank you.