# Natural Language Toolkit: Relation Extraction
#
# Copyright (C) 2001-2015 NLTK Project
# Author: Ewan Klein <ewan@inf.ed.ac.uk>
# URL: <http://nltk.org/>
# For license information, see LICENSE.TXT
"""
Code for extracting relational triples from the ieer and conll2002 corpora.
Relations are stored internally as dictionaries ('reldicts').
The two serialization outputs are "rtuple" and "clause".
- An rtuple is a tuple of the form ``(subj, filler, obj)``,
where ``subj`` and ``obj`` are pairs of Named Entity mentions, and ``filler`` is the string of words
occurring between ``sub`` and ``obj`` (with no intervening NEs). Strings are printed via ``repr()`` to
circumvent locale variations in rendering utf-8 encoded strings.
- A clause is an atom of the form ``relsym(subjsym, objsym)``,
where the relation, subject and object have been canonicalized to single strings.
"""
from __future__ import print_function
# todo: get a more general solution to canonicalized symbols for clauses -- maybe use xmlcharrefs?
from collections import defaultdict
import re
from nltk.compat import htmlentitydefs
# Dictionary that associates corpora with NE classes
NE_CLASSES = {
'ieer': ['LOCATION', 'ORGANIZATION', 'PERSON', 'DURATION',
'DATE', 'CARDINAL', 'PERCENT', 'MONEY', 'MEASURE'],
'conll2002': ['LOC', 'PER', 'ORG'],
'ace': ['LOCATION', 'ORGANIZATION', 'PERSON', 'DURATION',
'DATE', 'CARDINAL', 'PERCENT', 'MONEY', 'MEASURE', 'FACILITY', 'GPE'],
}
# Allow abbreviated class labels
short2long = dict(LOC = 'LOCATION', ORG = 'ORGANIZATION', PER = 'PERSON')
long2short = dict(LOCATION ='LOC', ORGANIZATION = 'ORG', PERSON = 'PER')
def _expand(type):
"""
Expand an NE class name.
:type type: str
:rtype: str
"""
try:
return short2long[type]
except KeyError:
return type
def class_abbrev(type):
"""
Abbreviate an NE class name.
:type type: str
:rtype: str
"""
try:
return long2short[type]
except KeyError:
return type
def _join(lst, sep=' ', untag=False):
"""
Join a list into a string, turning tags tuples into tag strings or just words.
:param untag: if ``True``, omit the tag from tagged input strings.
:type lst: list
:rtype: str
"""
try:
return sep.join(lst)
except TypeError:
if untag:
return sep.join(tup[0] for tup in lst)
from nltk.tag import tuple2str
return sep.join(tuple2str(tup) for tup in lst)
def descape_entity(m, defs=htmlentitydefs.entitydefs):
"""
Translate one entity to its ISO Latin value.
Inspired by example from effbot.org
"""
#s = 'mcglashan_&_sarrail'
#l = ['mcglashan', '&', 'sarrail']
#pattern = re.compile("&(\w+?);")
#new = list2sym(l)
#s = pattern.sub(descape_entity, s)
#print s, new
try:
return defs[m.group(1)]
except KeyError:
return m.group(0) # use as is
def list2sym(lst):
"""
Convert a list of strings into a canonical symbol.
:type lst: list
:return: a Unicode string without whitespace
:rtype: unicode
"""
sym = _join(lst, '_', untag=True)
sym = sym.lower()
ENT = re.compile("&(\w+?);")
sym = ENT.sub(descape_entity, sym)
sym = sym.replace('.', '')
return sym
def tree2semi_rel(tree):
"""
Group a chunk structure into a list of 'semi-relations' of the form (list(str), ``Tree``).
In order to facilitate the construction of (``Tree``, string, ``Tree``) triples, this
identifies pairs whose first member is a list (possibly empty) of terminal
strings, and whose second member is a ``Tree`` of the form (NE_label, terminals).
:param tree: a chunk tree
:return: a list of pairs (list(str), ``Tree``)
:rtype: list of tuple
"""
from nltk.tree import Tree
semi_rels = []
semi_rel = [[], None]
for dtr in tree:
if not isinstance(dtr, Tree):
semi_rel[0].append(dtr)
else:
# dtr is a Tree
semi_rel[1] = dtr
semi_rels.append(semi_rel)
semi_rel = [[], None]
return semi_rels
def semi_rel2reldict(pairs, window=5, trace=False):
"""
Converts the pairs generated by ``tree2semi_rel`` into a 'reldict': a dictionary which
stores information about the subject and object NEs plus the filler between them.
Additionally, a left and right context of length =< window are captured (within
a given input sentence).
:param pairs: a pair of list(str) and ``Tree``, as generated by
:param window: a threshold for the number of items to include in the left and right context
:type window: int
:return: 'relation' dictionaries whose keys are 'lcon', 'subjclass', 'subjtext', 'subjsym', 'filler', objclass', objtext', 'objsym' and 'rcon'
:rtype: list(defaultdict)
"""
result = []
while len(pairs) > 2:
reldict = defaultdict(str)
reldict['lcon'] = _join(pairs[0][0][-window:])
reldict['subjclass'] = pairs[0][1].label()
reldict['subjtext'] = _join(pairs[0][1].leaves())
reldict['subjsym'] = list2sym(pairs[0][1].leaves())
reldict['filler'] = _join(pairs[1][0])
reldict['untagged_filler'] = _join(pairs[1][0], untag=True)
reldict['objclass'] = pairs[1][1].label()
reldict['objtext'] = _join(pairs[1][1].leaves())
reldict['objsym'] = list2sym(pairs[1][1].leaves())
reldict['rcon'] = _join(pairs[2][0][:window])
if trace:
print("(%s(%s, %s)" % (reldict['untagged_filler'], reldict['subjclass'], reldict['objclass']))
result.append(reldict)
pairs = pairs[1:]
return result
[docs]def rtuple(reldict, lcon=False, rcon=False):
"""
Pretty print the reldict as an rtuple.
:param reldict: a relation dictionary
:type reldict: defaultdict
"""
items = [class_abbrev(reldict['subjclass']), reldict['subjtext'], reldict['filler'], class_abbrev(reldict['objclass']), reldict['objtext']]
format = '[%s: %r] %r [%s: %r]'
if lcon:
items = [reldict['lcon']] + items
format = '...%r)' + format
if rcon:
items.append(reldict['rcon'])
format = format + '(%r...'
printargs = tuple(items)
return format % printargs
[docs]def clause(reldict, relsym):
"""
Print the relation in clausal form.
:param reldict: a relation dictionary
:type reldict: defaultdict
:param relsym: a label for the relation
:type relsym: str
"""
items = (relsym, reldict['subjsym'], reldict['objsym'])
return "%s(%r, %r)" % items
#######################################################
# Demos of relation extraction with regular expressions
#######################################################
############################################
# Example of in(ORG, LOC)
############################################
def in_demo(trace=0, sql=True):
"""
Select pairs of organizations and locations whose mentions occur with an
intervening occurrence of the preposition "in".
If the sql parameter is set to True, then the entity pairs are loaded into
an in-memory database, and subsequently pulled out using an SQL "SELECT"
query.
"""
from nltk.corpus import ieer
if sql:
try:
import sqlite3
connection = sqlite3.connect(":memory:")
connection.text_factory = sqlite3.OptimizedUnicode
cur = connection.cursor()
cur.execute("""create table Locations
(OrgName text, LocationName text, DocID text)""")
except ImportError:
import warnings
warnings.warn("Cannot import sqlite; sql flag will be ignored.")
IN = re.compile(r'.*\bin\b(?!\b.+ing)')
print()
print("IEER: in(ORG, LOC) -- just the clauses:")
print("=" * 45)
for file in ieer.fileids():
for doc in ieer.parsed_docs(file):
if trace:
print(doc.docno)
print("=" * 15)
for rel in extract_rels('ORG', 'LOC', doc, corpus='ieer', pattern=IN):
print(clause(rel, relsym='IN'))
if sql:
try:
rtuple = (rel['subjtext'], rel['objtext'], doc.docno)
cur.execute("""insert into Locations
values (?, ?, ?)""", rtuple)
connection.commit()
except NameError:
pass
if sql:
try:
cur.execute("""select OrgName from Locations
where LocationName = 'Atlanta'""")
print()
print("Extract data from SQL table: ORGs in Atlanta")
print("-" * 15)
for row in cur:
print(row)
except NameError:
pass
############################################
# Example of has_role(PER, LOC)
############################################
def roles_demo(trace=0):
from nltk.corpus import ieer
roles = """
(.*( # assorted 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)
print()
print("IEER: has_role(PER, ORG) -- raw rtuples:")
print("=" * 45)
for file in ieer.fileids():
for doc in ieer.parsed_docs(file):
lcon = rcon = False
if trace:
print(doc.docno)
print("=" * 15)
lcon = rcon = True
for rel in extract_rels('PER', 'ORG', doc, corpus='ieer', pattern=ROLES):
print(rtuple(rel, lcon=lcon, rcon=rcon))
##############################################
### Show what's in the IEER Headlines
##############################################
def ieer_headlines():
from nltk.corpus import ieer
from nltk.tree import Tree
print("IEER: First 20 Headlines")
print("=" * 45)
trees = [(doc.docno, doc.headline) for file in ieer.fileids() for doc in ieer.parsed_docs(file)]
for tree in trees[:20]:
print()
print("%s:\n%s" % tree)
#############################################
## Dutch CONLL2002: take_on_role(PER, ORG
#############################################
def conllned(trace=1):
"""
Find the copula+'van' relation ('of') in the Dutch tagged training corpus
from CoNLL 2002.
"""
from nltk.corpus import conll2002
vnv = """
(
is/V| # 3rd sing present and
was/V| # past forms of the verb zijn ('be')
werd/V| # and also present
wordt/V # past of worden ('become)
)
.* # followed by anything
van/Prep # followed by van ('of')
"""
VAN = re.compile(vnv, re.VERBOSE)
print()
print("Dutch CoNLL2002: van(PER, ORG) -- raw rtuples with context:")
print("=" * 45)
for doc in conll2002.chunked_sents('ned.train'):
lcon = rcon = False
if trace:
lcon = rcon = True
for rel in extract_rels('PER', 'ORG', doc, corpus='conll2002', pattern=VAN, window=10):
print(rtuple(rel, lcon=True, rcon=True))
#############################################
## Spanish CONLL2002: (PER, ORG)
#############################################
def conllesp():
from nltk.corpus import conll2002
de = """
.*
(
de/SP|
del/SP
)
"""
DE = re.compile(de, re.VERBOSE)
print()
print("Spanish CoNLL2002: de(ORG, LOC) -- just the first 10 clauses:")
print("=" * 45)
rels = [rel for doc in conll2002.chunked_sents('esp.train')
for rel in extract_rels('ORG', 'LOC', doc, corpus='conll2002', pattern = DE)]
for r in rels[:10]: print(clause(r, relsym='DE'))
print()
def ne_chunked():
print()
print("1500 Sentences from Penn Treebank, as processed by NLTK NE Chunker")
print("=" * 45)
ROLE = re.compile(r'.*(chairman|president|trader|scientist|economist|analyst|partner).*')
rels = []
for i, sent in enumerate(nltk.corpus.treebank.tagged_sents()[:1500]):
sent = nltk.ne_chunk(sent)
rels = extract_rels('PER', 'ORG', sent, corpus='ace', pattern=ROLE, window=7)
for rel in rels:
print('{0:<5}{1}'.format(i, rtuple(rel)))
if __name__ == '__main__':
import nltk
from nltk.sem import relextract
in_demo(trace=0)
roles_demo(trace=0)
conllned()
conllesp()
ieer_headlines()
ne_chunked()