def relationBetweenEntities(sentences):
tokenized_sentences = [word_tokenize(sentence) for sentence in sentences]
tagged_sentences = [
nltk.tag.pos_tag(sentence) for sentence in tokenized_sentences
]
OF = re.compile(r'.*\bof\b.*')
IN = re.compile(r'.*\bin\b(?!\b.+ing)')
print('PERSON-ORGANISATION Relationships:')
for i, sent in enumerate(tagged_sentences):
sent = nltk.chunk.ne_chunk(
sent) # ne_chunk method expects one tagged sentence
rels = extract_rels('PER',
'ORG',
sent,
corpus='ace',
pattern=IN,
window=10)
for rel in rels:
print(rtuple(rel))
print('PERSON-GPE Relationships:')
for i, sent in enumerate(tagged_sentences):
sent = nltk.chunk.ne_chunk(
sent) # ne_chunk method expects one tagged sentence
rels = extract_rels('PER',
'GPE',
sent,
corpus='ace',
pattern=OF,
window=10)
for rel in rels:
print(rtuple(rel))
def extractRel(reldicts,subjclass,objclass,window,pattern):
relfilter = lambda x: (x['subjclass'] == subjclass and
len(x['filler'].split()) <= window and
pattern.match(x['filler']) and
x['objclass'] == objclass)
for rel in list(filter(relfilter, reldicts)):
print(relextract.rtuple(rel))
reldicts = relextract.semi_rel2reldict(pairs)
for k, v in sorted(reldicts[0].items()):
print(k, '=>', v)
# The function relextract() allows us to filter the reldicts
# according to the classes of the subject and object named entities.
# In addition, we can specify that the filler text has to match a given regular expression,
# as illustrated in the next example. Here, we are looking for pairs of entities in the IN
# relation, where IN has signature <ORG, LOC>.
IN = re.compile(r'(\s?[a-z].*)?\bin\b(?!\b.+ing\b)')
for fileid in ieer.fileids():
print fileid
for doc in ieer.parsed_docs(fileid):
for rel in relextract.extract_rels('ORG',
'LOC',
doc,
corpus='ieer',
pattern=IN):
print(relextract.rtuple(rel)) # doctest: +ELLIPSIS
roles = "(.*(analyst|commissioner|professor|researcher|(spokes|chair)(wo)?m(e|a)n|writer|secretary|manager|commander|boss|founder)\s(of|in|for) (the)?)"
ROLES = re.compile(roles, re.VERBOSE)
for fileid in ieer.fileids():
for doc in ieer.parsed_docs(fileid):
for rel in relextract.extract_rels('PER',
'ORG',
doc,
corpus='ieer',
pattern=ROLES):
print(relextract.rtuple(rel)) # doctest: +ELLIPSIS
def main():
print "user input(1) or semcor(2)?"
num = raw_input()
if num == "1":
#input
print "enter word"
word = raw_input()
for meaning in (net.synsets(word)):
#print "Sense: " + re.findall("'.*'", str(meaning))[0]
print "Sense: " + str(meaning)
print meaning.definition() + "\n"
hypernyms = (meaning.hypernyms())
if len(hypernyms) > 0:
print "\nHypernyms:"
for meaning2 in hypernyms:
print re.findall("'.*'", str(meaning2))[0]
hyponyms = (meaning.hyponyms())
if len(hyponyms) > 0:
print "\nHyponyms:"
for meaning2 in hyponyms:
print re.findall("'.*'", str(meaning2))[0]
# print "\nHypernym Tree:"
# print (gethypernymtree(meaning))
print "\n"
# dog = wn.synset('dog.n.01')
# hypo = lambda s: s.hyponyms()
# hyper = lambda s: s.hypernyms()
#list(dog.closure(s.hypernyms(), depth=1)) == dog.hypernyms()
#True
#>>> list(dog.closure(hyper, depth=1)) == dog.hypernyms()
elif (num == "2"):
#semcor
print "semcor"
for line in semcor.sents()[0:100]:
s = ""
for word in line:
s = s + " " + word
print s + "\n"
for word in line:
meanings = net.synsets(word)
if len(meanings) > 0:
print meanings[0].definition()
elif num == "3":
docs = ieer.parsed_docs('APW_19980424')
tree = docs[1].text
from nltk.sem import relextract
pairs = relextract.tree2semi_rel(tree)
for s, tree in pairs[18:22]:
print('("...%s", %s)' % (" ".join(s[-5:]), tree))
reldicts = relextract.semi_rel2reldict(pairs)
for k, v in sorted(reldicts[0].items()):
print(k, '=>', v)
# The function relextract() allows us to filter the reldicts
# according to the classes of the subject and object named entities.
# In addition, we can specify that the filler text has to match a given regular expression,
# as illustrated in the next example. Here, we are looking for pairs of entities in the IN
# relation, where IN has signature <ORG, LOC>.
IN = re.compile(r'(\s?[a-z].*)?\bin\b(?!\b.+ing\b)')
for fileid in ieer.fileids():
print fileid
for doc in ieer.parsed_docs(fileid):
for rel in relextract.extract_rels('ORG',
'LOC',
doc,
corpus='ieer',
pattern=IN):
print(relextract.rtuple(rel)) # doctest: +ELLIPSIS
roles = "(.*(analyst|commissioner|professor|researcher|(spokes|chair)(wo)?m(e|a)n|writer|secretary|manager|commander|boss|founder)\s(of|in|for) (the)?)"
ROLES = re.compile(roles, re.VERBOSE)
for fileid in ieer.fileids():
for doc in ieer.parsed_docs(fileid):
for rel in relextract.extract_rels('PER',
'ORG',
doc,
corpus='ieer',
pattern=ROLES):
print(relextract.rtuple(rel)) # doctest: +ELLIPSIS
# Eg: "about first-level questions, said Ms." => string
# (PERSON Cohn) => named entity, which is a tree. Root is PERSON, and child node is Cohn
pairs = relextract.tree2semi_rel(tree)
""" for s, tree in pairs[:3]:
print('*'*20)
print(' '.join(s))
print(tree) """
# Processes three of the above pairs at a time into a dictionary. Eg: (string1, tree1) (string2, tree2) (string3, tree3)
# string1 is stored as left context.
# tree1 is the subject, string2 is the filler, and tree2 is the object.
# string3 is stored as right context.
reldicts = relextract.semi_rel2reldict(pairs)
for r in reldicts:
print('=' * 20)
print(r['subjtext']) # Print the subject text
print(r['filler']) # Print the filler information
print(r['objtext']) # Print the object text
# Matches any number of characters followed by the word "in" as long as "in" is not followed by a word ending in "ing"
IN = re.compile(r'.*\bin\b(?!\b.+ing\b)')
# Finds relationships of the form entity1 IN entity2, where entity1 is ORGANIZATION and entity2 is LOCATION
print('\nRelation of type ORGANIZATION in LOCATION: \n')
for relation in relextract.extract_rels('ORG',
'LOC',
docs[1],
corpus='ieer',
pattern=IN):
print(relextract.rtuple(relation))
def createDoc(text):#To create a DOCUMENT by combining all the chunked sentences.
chunkedSents=list()
for sent in nltk.sent_tokenize(text):
chunkedSents+=[chunk for chunk in nltk.ne_chunk(nltk.pos_tag(nltk.word_tokenize(sent)))]
docTree=nltk.Tree('DOCUMENT',chunkedSents)
pairs=relextract.tree2semi_rel(docTree)
for sent,tree in pairs:
print '("...%s", %s)' % (' '.join([word for word,tag in sent][-5:]),tree) # To print
reldicts = relextract.semi_rel2reldict(pairs)
for r in reldicts:
print '='*30
print(r['subjclass'],':', r['subjtext'])
print (r['filler'])
print (r['objclass'],':', r['objtext'])
# Match pattern in filler
roles = """
(.*(
analyst|
chair(wo)?man|
commissioner|
counsel|
director|
economist|
editor|
executive|
foreman|
governor|
head|
lawyer|
leader|
librarian).*)|
manager|
partner|
president|
producer|
professor|
researcher|
spokes(wo)?man|
writer|
,\sof\sthe?\s*
"""# "X, of (the) Y"
ROLES = re.compile(roles, re.VERBOSE)
IN = re.compile(r'.*\bin\b(?!\b.+ing\b)')
pattern=ROLES
subjclass='PERSON'#'ORGANIZATION'
objclass='ORGANIZATION'#'GPE'
window=10
relfilter = lambda x: (x['subjclass'] == subjclass and
len(x['filler'].split()) <= window and
pattern.match(x['filler']) and
x['objclass'] == objclass)
for rel in list(filter(relfilter, reldicts)):
print(relextract.rtuple(rel))
def improve(reldicts):
for dicts in reldicts:
print len(nltk.sent_tokenize(dicts['filler']))
improve(reldicts)
#print pairs[0]
#print pairs[1]
#print pairs[2]
#for sent,tree in pairs[0]:
# print sent,tree
#print('("...%s", %s)' % (" ".join(sent[0][-5:]),tree))
#tree=nltk.ne_chunk(nltk.pos_tag(nltk.word_tokenize( nltk.sent_tokenize(text)[24] )))
#l=[chunk for chunk in tree]
#print "%s"%docTree
"""
from nltk import ne_chunk, pos_tag, word_tokenize
from nltk.sem.relextract import extract_rels, rtuple
text = BookText(url1)
BELONG = re.compile(r'.*\bin|from|belonged|lived\b.*')
sentences = nltk.sent_tokenize(text)
tokenized_sentences = [nltk.word_tokenize(sentence) for sentence in sentences]
tagged_sentences = [nltk.pos_tag(sentence) for sentence in tokenized_sentences]
for i,sent in enumerate(tagged_sentences):
sent = ne_chunk(sent)
rels = extract_rels('PER', 'GPE', sent, corpus = 'ace', pattern = BELONG, window = 10)
for rel in rels:
print(rtuple(rel))
[PER: 'elizabeth/NNP'] 'lived/VBN in/IN' [GPE: 'london/NNP']
[PER: 'jane/NNP'] 'lived/VBN near/IN' [GPE: 'neitherfield/NNP']
[PER: 'bingley/NNP'] 'is/VBZ from/IN' [GPE: 'scotland/NNP']
[PER: 'elizabeth/NNP'] 'belonged/VBD to/IN' [GPE: 'london/NNP']
[PER: 'jane/NNP'] 'was/VBD now/RB in/IN' [GPE: 'brighton/NNP']
RELATIONS = re.compile(r'.*\mother|father|sister|brother|aunt|uncle\b.*')
for i,sent in enumerate(tagged_sentences):
sent = ne_chunk(sent)
rels = extract_rels('PER', 'PER', sent, corpus = 'ace', pattern = BELONG, window = 10)
for rel in rels:
print(rtuple(rel))
