You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
51 lines
1.7 KiB
51 lines
1.7 KiB
# Natural Language Toolkit: Word Sense Disambiguation Algorithms
|
|
#
|
|
# Authors: Liling Tan <alvations@gmail.com>,
|
|
# Dmitrijs Milajevs <dimazest@gmail.com>
|
|
#
|
|
# Copyright (C) 2001-2019 NLTK Project
|
|
# URL: <http://nltk.org/>
|
|
# For license information, see LICENSE.TXT
|
|
|
|
from nltk.corpus import wordnet
|
|
|
|
|
|
def lesk(context_sentence, ambiguous_word, pos=None, synsets=None):
|
|
"""Return a synset for an ambiguous word in a context.
|
|
|
|
:param iter context_sentence: The context sentence where the ambiguous word
|
|
occurs, passed as an iterable of words.
|
|
:param str ambiguous_word: The ambiguous word that requires WSD.
|
|
:param str pos: A specified Part-of-Speech (POS).
|
|
:param iter synsets: Possible synsets of the ambiguous word.
|
|
:return: ``lesk_sense`` The Synset() object with the highest signature overlaps.
|
|
|
|
This function is an implementation of the original Lesk algorithm (1986) [1].
|
|
|
|
Usage example::
|
|
|
|
>>> lesk(['I', 'went', 'to', 'the', 'bank', 'to', 'deposit', 'money', '.'], 'bank', 'n')
|
|
Synset('savings_bank.n.02')
|
|
|
|
[1] Lesk, Michael. "Automatic sense disambiguation using machine
|
|
readable dictionaries: how to tell a pine cone from an ice cream
|
|
cone." Proceedings of the 5th Annual International Conference on
|
|
Systems Documentation. ACM, 1986.
|
|
http://dl.acm.org/citation.cfm?id=318728
|
|
"""
|
|
|
|
context = set(context_sentence)
|
|
if synsets is None:
|
|
synsets = wordnet.synsets(ambiguous_word)
|
|
|
|
if pos:
|
|
synsets = [ss for ss in synsets if str(ss.pos()) == pos]
|
|
|
|
if not synsets:
|
|
return None
|
|
|
|
_, sense = max(
|
|
(len(context.intersection(ss.definition().split())), ss) for ss in synsets
|
|
)
|
|
|
|
return sense
|