You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
69 lines
2.9 KiB
Plaintext
69 lines
2.9 KiB
Plaintext
5 years ago
|
.. Copyright (C) 2001-2019 NLTK Project
|
||
|
|
.. For license information, see LICENSE.TXT
|
||
|
|
|
||
|
|
.. -*- coding: utf-8 -*-
|
||
|
|
|
||
|
|
=========================
|
||
|
|
Word Sense Disambiguation
|
||
|
|
=========================
|
||
|
|
|
||
|
|
|
||
|
|
Lesk Algorithm
|
||
|
|
--------------
|
||
|
|
|
||
|
|
|
||
|
|
Performs the classic Lesk algorithm for Word Sense Disambiguation (WSD) using
|
||
|
|
a the definitions of the ambiguous word.
|
||
|
|
|
||
|
|
Given an ambiguous word and the context in which the word occurs, Lesk returns
|
||
|
|
a Synset with the highest number of overlapping words between the context
|
||
|
|
sentence and different definitions from each Synset.
|
||
|
|
|
||
|
|
>>> from nltk.wsd import lesk
|
||
|
|
>>> sent = ['I', 'went', 'to', 'the', 'bank', 'to', 'deposit', 'money', '.']
|
||
|
|
|
||
|
|
>>> print(lesk(sent, 'bank', 'n'))
|
||
|
|
Synset('savings_bank.n.02')
|
||
|
|
|
||
|
|
>>> print(lesk(sent, 'bank'))
|
||
|
|
Synset('savings_bank.n.02')
|
||
|
|
|
||
|
|
The definitions for "bank" are:
|
||
|
|
|
||
|
|
>>> from nltk.corpus import wordnet as wn
|
||
|
|
>>> for ss in wn.synsets('bank'):
|
||
|
|
... print(ss, ss.definition())
|
||
|
|
...
|
||
|
|
Synset('bank.n.01') sloping land (especially the slope beside a body of water)
|
||
|
|
Synset('depository_financial_institution.n.01') a financial institution that accepts deposits and channels the money into lending activities
|
||
|
|
Synset('bank.n.03') a long ridge or pile
|
||
|
|
Synset('bank.n.04') an arrangement of similar objects in a row or in tiers
|
||
|
|
Synset('bank.n.05') a supply or stock held in reserve for future use (especially in emergencies)
|
||
|
|
Synset('bank.n.06') the funds held by a gambling house or the dealer in some gambling games
|
||
|
|
Synset('bank.n.07') a slope in the turn of a road or track; the outside is higher than the inside in order to reduce the effects of centrifugal force
|
||
|
|
Synset('savings_bank.n.02') a container (usually with a slot in the top) for keeping money at home
|
||
|
|
Synset('bank.n.09') a building in which the business of banking transacted
|
||
|
|
Synset('bank.n.10') a flight maneuver; aircraft tips laterally about its longitudinal axis (especially in turning)
|
||
|
|
Synset('bank.v.01') tip laterally
|
||
|
|
Synset('bank.v.02') enclose with a bank
|
||
|
|
Synset('bank.v.03') do business with a bank or keep an account at a bank
|
||
|
|
Synset('bank.v.04') act as the banker in a game or in gambling
|
||
|
|
Synset('bank.v.05') be in the banking business
|
||
|
|
Synset('deposit.v.02') put into a bank account
|
||
|
|
Synset('bank.v.07') cover with ashes so to control the rate of burning
|
||
|
|
Synset('trust.v.01') have confidence or faith in
|
||
|
|
|
||
|
|
Test disambiguation of POS tagged `able`.
|
||
|
|
|
||
|
|
>>> [(s, s.pos()) for s in wn.synsets('able')]
|
||
|
|
[(Synset('able.a.01'), 'a'), (Synset('able.s.02'), 's'), (Synset('able.s.03'), 's'), (Synset('able.s.04'), 's')]
|
||
|
|
>>> sent = 'people should be able to marry a person of their choice'.split()
|
||
|
|
>>> lesk(sent, 'able')
|
||
|
|
Synset('able.s.04')
|
||
|
|
>>> lesk(sent, 'able', pos='a')
|
||
|
|
Synset('able.a.01')
|
||
|
|
|
||
|
|
Test behavior if there is are no matching senses.
|
||
|
|
|
||
|
|
>>> lesk('John loves Mary'.split(), 'loves', synsets=[])
|