Retrieving Tags From Result Of Pos Tagging

Using python how to retrieve only the tags - 'NN', 'JJ' etc from ('[', 'NN'), ('u'Tradus-Under', 'NN'), (''', ''''), (',', ','), ('u'Maintenance', 'JJ'), (''', ''''), (']', '

Solution 1:

Assuming those elements are in a list (I call that list lst):

importstring
lst = [
    ('[', 'NN'),
    ("u'Tradus-Under", 'NN'),
    ("'", "''"),
    (',', ','),
    ("u'Maintenance", 'JJ'),
    ("'", "''"),
    (']', ':')
]

tags = []
for _,poss_tag in lst:
    if(len(poss_tag) == 2 and 
           poss_tag[0] == poss_tag[1] and 
           poss_tag[0] in string.ascii_letters):
        tags.append(poss_tag)

print(tags)

Output:

['NN', 'NN', 'JJ']

If you want a unique set, you could bounce it to a set and back:

print(list(set(tags)))

Output:

['JJ', 'NN']