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 rels2rdf(ns, verbose=False):
"""
Convert the reldicts derived from the IEER corpus in an RDF Graph.
"""
graph = ConjunctiveGraph()
graph.bind('nltk',BASE)
graph.bind('org', "http://nltk.org/terms/org#")
graph.bind('loc', "http://nltk.org/terms/loc#")
graph.bind('pred', "http://nltk.org/terms/pred#")
graph.bind('class', "http://nltk.org/terms/class#")
in_uri = sym2uri(ns, 'pred', 'in')
loc_uri = sym2uri(ns, 'class', 'Location')
org_uri = sym2uri(ns, 'class', 'Organization')
graph.add((in_uri, RDFNS.type, RDFSNS.Property))
graph.add((loc_uri, RDFNS.type, RDFSNS.Class))
graph.add((org_uri, RDFNS.type, RDFSNS.Class))
graph.add((in_uri, RDFSNS.domain, org_uri))
graph.add((in_uri, RDFSNS.range, loc_uri))
from nltk.corpus import ieer
IN = re.compile(r'.*\bin\b(?!\b.+ing\b)')
for item in ieer.fileids():
for doc in ieer.parsed_docs(item):
for reldict in extract_rels('ORG', 'LOC', doc, corpus='ieer', pattern=IN):
graph.add(make_rdf(ns, reldict, relsym='in'))
for triple in make_rdfs(ns, reldict):
graph.add(triple)
return graph
def findrelations(text):
roles = """
(.*(
computer scientist|
led |
adjunct professor).*)|
co-founder|
chairman|
parents|
,\sof\sthe?\s* # "X, of (the) Y"
"""
ROLES = re.compile(roles, re.VERBOSE)
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
]
chunked_sentences = nltk.ne_chunk_sents(tagged_sentences)
for doc in chunked_sentences:
print(doc)
for rel in relextract.extract_rels('PER',
'ORG',
doc,
corpus='ace',
pattern=ROLES):
#it is a tree, so you need to work on it to output what you want
print(relextract.show_raw_rtuple(rel))
def rels2rdf(ns, verbose=False):
"""
Convert the reldicts derived from the IEER corpus in an RDF Graph.
"""
graph = ConjunctiveGraph()
graph.bind("nltk", BASE)
graph.bind("org", "http://nltk.org/terms/org#")
graph.bind("loc", "http://nltk.org/terms/loc#")
graph.bind("pred", "http://nltk.org/terms/pred#")
graph.bind("class", "http://nltk.org/terms/class#")
in_uri = sym2uri(ns, "pred", "in")
loc_uri = sym2uri(ns, "class", "Location")
org_uri = sym2uri(ns, "class", "Organization")
graph.add((in_uri, RDFNS.type, RDFSNS.Property))
graph.add((loc_uri, RDFNS.type, RDFSNS.Class))
graph.add((org_uri, RDFNS.type, RDFSNS.Class))
graph.add((in_uri, RDFSNS.domain, org_uri))
graph.add((in_uri, RDFSNS.range, loc_uri))
from nltk.corpus import ieer
IN = re.compile(r".*\bin\b(?!\b.+ing\b)")
for item in ieer.fileids():
for doc in ieer.parsed_docs(item):
for reldict in extract_rels("ORG", "LOC", doc, corpus="ieer", pattern=IN):
graph.add(make_rdf(ns, reldict, relsym="in"))
for triple in make_rdfs(ns, reldict):
graph.add(triple)
return graph
def _nltk_extract(self, subj, obj):
"""Use NLTK's built-in relationship extractor to get subj and obj
named entity relationships and context."""
re_location = re.compile(".*")
result = []
for sent in self._sents:
extraction = relextract.extract_rels(subj, obj, sent, pattern=re_location)
if extraction:
result.append(extraction)
return result
def _nltk_extract(self, subj, obj):
"""Use NLTK's built-in relationship extractor to get subj and obj
named entity relationships and context."""
re_location = re.compile(".*")
result = []
for sent in self._sents:
extraction = relextract.extract_rels(
subj,
obj,
sent,
pattern=re_location,
)
if extraction:
result.append(extraction)
return result
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
exit()
except UnicodeDecodeError:
print "Retrieved book not in proper encoding. Exiting program.\n"
exit()
print "Book retrieved - URL: https://www.gutenberg.org/ebooks/" + str(
book_num)
reg_ex = re.compile(r'.*')
s = book_data
print "\nTokenizing book data"
s = word_tokenize(s)
text_with_tags = nltk.pos_tag(s)
text_chunk = nltk.ne_chunk(text_with_tags)
person_location_pairs = {}
print "Searching Name - Location interections"
for rel in relextract.extract_rels('PER',
'GPE',
text_chunk,
pattern=reg_ex):
relation = nltk.sem.rtuple(rel)
person_location = get_person_location(relation)
if person_location in person_location_pairs:
current_pair = person_location_pairs[person_location]
person_location_pairs[person_location] = current_pair + 1
else:
person_location_pairs[person_location] = 1
if len(person_location_pairs) == 0:
print "No interaction found in this book."
exit()
print "\n----------------------------------------------------"
print "Interaction frequencies (Descending order)"
print "(Person - Location : Count)"
print "----------------------------------------------------"
for k, v in sorted(reldicts[0].items()):
print(k, '=>', v) # doctest: +ELLIPSIS
for r in reldicts[18:20]:
print('=' * 20)
print(r['subjtext'])
print(r['filler'])
print(r['objtext'])
import re
IN = re.compile(r'.*\bin\b(?!\b.+ing\b)')
for fileid in ieer.fileids():
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|
chair(wo)?man|
commissioner|
counsel|
director|
economist|
editor|
executive|
foreman|
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
# Converts chunk (NER is already done) into list of two-member lists. Each contains a string followed by a tree (named entity)
# 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))
import re
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:
