POS Tagging in NLP

Question

I am doing a course in NLTK Python which has a hands-on problem(on Katacoda) on "Text Corpora" and it is not accepting my solution mentioned below. Have been stuck on this problem since long. Need to complete this hands-on to proceed foreword in course.

Problem Defenition

Import the text corpus brown.
Extract the list of tagged words from the corpus brown. Store the result in brown_tagged_words
Generate trigrams of brown_tagged_words and store the result in brown_tagged_trigrams.

4.For every trigram of brown_tagged_trigrams, determine the tags associated with each word. This results in a list of tuples, where each tuple contain pos tags of 3 consecutive words, occurring in text. Store the result in brown_trigram_pos_tags.

5.Determine the frequency distribution of brown_trigram_pos_tags and store the result in brown_trigram_pos_tags_freq. 6.Print the number of occurrences of trigram ('JJ','NN','IN')

For this I have tried below solution:

import nltk
from nltk.corpus import brown
brown_tagged_words = [w for w in brown.tagged_words()]
brown_tagged_trigrams = nltk.trigrams(brown_tagged_words)
brown_trigram_pos_tags = [(w1[1],w2[1],w2[1]) for w1,w2,w3 in brown_tagged_trigrams]
brown_trigram_pos_tags_freq = nltk.FreqDist(brown_trigram_pos_tags)
print(brown_trigram_pos_tags_freq[('JJ', 'NN', 'IN')])

But what is your question? Have you read about [How to ask](https://stackoverflow.com/help/how-to-ask)? — DYZ, May 12 '19 at 03:51

score 1 · Accepted Answer · edited Sep 22 '19 at 07:38

1

brown_trigram_pos_tags = [(w1[1],w2[1],w3[1]) for w1,w2,w3 in brown_tagged_trigrams]

Here change W2 to w3,this will give value around 8

edited Sep 22 '19 at 07:38

Trenton McKinney

56,955
33
144
158

answered Sep 22 '19 at 06:49

Karthik

26
1

score 0 · Answer 2 · answered May 13 '19 at 09:35

0

Try this:-

('IN', 'AT', 'AT')

You will get the result: 43271

you are getting 0 because there is no occurrence of ('JJ', 'NN', 'IN').

answered May 13 '19 at 09:35

Chandan Gupta

684
4
11

1

Hello Chandan, I tried already as you referred, But its not accepting as Solution..Got message as Please Continue your task before Proceeding. I couldn't understand the statement, "occurring in text". – Muralitharan Sathyamoorthy May 13 '19 at 12:18
I mean to saw that there is no combination of ('JJ', 'NN', 'IN') in brown corpus text which you are looking for. – Chandan Gupta May 13 '19 at 14:06
1

Got your Point, But Couldn't able finish this task Yet. – Muralitharan Sathyamoorthy May 15 '19 at 09:05
@MuralitharanSathyamoorthy please explain your problem statement in detail. – Chandan Gupta May 15 '19 at 09:26
Which scenerio are you working on katacoda, I am not able to understand here. – Chandan Gupta May 16 '19 at 08:08
1

brown_trigram_pos_tags = [(w1[1],w2[1],w2[1]) for w1,w2,w3 in brown_tagged_trigrams] , it's typo Error instead w3, gave w2 in this line. Thanks. Finally found it. – Muralitharan Sathyamoorthy May 21 '19 at 16:01

score 0 · Answer 3 · answered May 24 '20 at 14:38

0

import nltk
from nltk.corpus import brown
brown_tagged_words = brown.tagged_words()
brown_tagged_trigrams = [(w1,w2,w3) for w1,w2,w3 in nltk.trigrams(brown_tagged_words)]
brown_trigram_pos_tags = [(w1[1],w2[1],w2[1]) for w1,w2,w3 in 
brown_tagged_trigrams]
brown_trigram_pos_tags_freq = nltk.FreqDist(brown_trigram_pos_tags)
print(brown_trigram_pos_tags_freq[('JJ', 'NN', 'IN')])

Try this...

answered May 24 '20 at 14:38

PKM

1

Welcome on Stack Overflow, while this may answer the question, it is better to give explanations and not only code for your answer. – gogaz May 24 '20 at 17:21

POS Tagging in NLP

Problem Defenition

3 Answers3