RiWordNet (RiTa) コード(メソッドを参照)を調べたところ、synsets、hyponyms、類似 tos、sees、および座標名getAllSynonymsのすべての補題を与えることによって同義語が生成されることがわかりました。座標名は入れませんでしたが、反意語を追加しました。さらに、synset 名と「同義語タイプ」をデータに追加して、定義や例などの他の Wordnet データを利用できるようにしました。Python での私のコードと出力は次のとおりです。
'''Synonym generator using NLTK WordNet Interface: http://www.nltk.org/howto/wordnet.html
'ss': synset
'hyp': hyponym
'sim': similar to
'ant': antonym
'also' also see
'''
from nltk.corpus import wordnet as wn
def get_all_synsets(word, pos=None):
for ss in wn.synsets(word):
for lemma in ss.lemma_names():
yield (lemma, ss.name())
def get_all_hyponyms(word, pos=None):
for ss in wn.synsets(word, pos=pos):
for hyp in ss.hyponyms():
for lemma in hyp.lemma_names():
yield (lemma, hyp.name())
def get_all_similar_tos(word, pos=None):
for ss in wn.synsets(word):
for sim in ss.similar_tos():
for lemma in sim.lemma_names():
yield (lemma, sim.name())
def get_all_antonyms(word, pos=None):
for ss in wn.synsets(word, pos=None):
for sslema in ss.lemmas():
for antlemma in sslema.antonyms():
yield (antlemma.name(), antlemma.synset().name())
def get_all_also_sees(word, pos=None):
for ss in wn.synsets(word):
for also in ss.also_sees():
for lemma in also.lemma_names():
yield (lemma, also.name())
def get_all_synonyms(word, pos=None):
for x in get_all_synsets(word, pos):
yield (x[0], x[1], 'ss')
for x in get_all_hyponyms(word, pos):
yield (x[0], x[1], 'hyp')
for x in get_all_similar_tos(word, pos):
yield (x[0], x[1], 'sim')
for x in get_all_antonyms(word, pos):
yield (x[0], x[1], 'ant')
for x in get_all_also_sees(word, pos):
yield (x[0], x[1], 'also')
for x in get_all_synonyms('love'):
print x
'love' と 'brave' の出力:
愛する
(u'love', u'love.n.01', 'ss')
(u'love', u'love.n.02', 'ss')
(u'passion', u'love.n.02', 'ss')
(u'beloved', u'beloved.n.01', 'ss')
(u'dear', u'beloved.n.01', 'ss')
(u'dearest', u'beloved.n.01', 'ss')
(u'honey', u'beloved.n.01', 'ss')
(u'love', u'beloved.n.01', 'ss')
(u'love', u'love.n.04', 'ss')
(u'sexual_love', u'love.n.04', 'ss')
(u'erotic_love', u'love.n.04', 'ss')
(u'love', u'love.n.05', 'ss')
(u'sexual_love', u'sexual_love.n.02', 'ss')
(u'lovemaking', u'sexual_love.n.02', 'ss')
(u'making_love', u'sexual_love.n.02', 'ss')
(u'love', u'sexual_love.n.02', 'ss')
(u'love_life', u'sexual_love.n.02', 'ss')
(u'love', u'love.v.01', 'ss')
(u'love', u'love.v.02', 'ss')
(u'enjoy', u'love.v.02', 'ss')
(u'love', u'love.v.03', 'ss')
(u'sleep_together', u'sleep_together.v.01', 'ss')
(u'roll_in_the_hay', u'sleep_together.v.01', 'ss')
(u'love', u'sleep_together.v.01', 'ss')
(u'make_out', u'sleep_together.v.01', 'ss')
(u'make_love', u'sleep_together.v.01', 'ss')
(u'sleep_with', u'sleep_together.v.01', 'ss')
(u'get_laid', u'sleep_together.v.01', 'ss')
(u'have_sex', u'sleep_together.v.01', 'ss')
(u'know', u'sleep_together.v.01', 'ss')
(u'do_it', u'sleep_together.v.01', 'ss')
(u'be_intimate', u'sleep_together.v.01', 'ss')
(u'have_intercourse', u'sleep_together.v.01', 'ss')
(u'have_it_away', u'sleep_together.v.01', 'ss')
(u'have_it_off', u'sleep_together.v.01', 'ss')
(u'screw', u'sleep_together.v.01', 'ss')
(u'fuck', u'sleep_together.v.01', 'ss')
(u'jazz', u'sleep_together.v.01', 'ss')
(u'eff', u'sleep_together.v.01', 'ss')
(u'hump', u'sleep_together.v.01', 'ss')
(u'lie_with', u'sleep_together.v.01', 'ss')
(u'bed', u'sleep_together.v.01', 'ss')
(u'have_a_go_at_it', u'sleep_together.v.01', 'ss')
(u'bang', u'sleep_together.v.01', 'ss')
(u'get_it_on', u'sleep_together.v.01', 'ss')
(u'bonk', u'sleep_together.v.01', 'ss')
(u'agape', u'agape.n.01', 'hyp')
(u'agape', u'agape.n.02', 'hyp')
(u'agape_love', u'agape.n.02', 'hyp')
(u'amorousness', u'amorousness.n.01', 'hyp')
(u'enamoredness', u'amorousness.n.01', 'hyp')
(u'ardor', u'ardor.n.02', 'hyp')
(u'ardour', u'ardor.n.02', 'hyp')
(u'benevolence', u'benevolence.n.01', 'hyp')
(u'devotion', u'devotion.n.01', 'hyp')
(u'devotedness', u'devotion.n.01', 'hyp')
(u'filial_love', u'filial_love.n.01', 'hyp')
(u'heartstrings', u'heartstrings.n.01', 'hyp')
(u'lovingness', u'lovingness.n.01', 'hyp')
(u'caring', u'lovingness.n.01', 'hyp')
(u'loyalty', u'loyalty.n.02', 'hyp')
(u'puppy_love', u'puppy_love.n.01', 'hyp')
(u'calf_love', u'puppy_love.n.01', 'hyp')
(u'crush', u'puppy_love.n.01', 'hyp')
(u'infatuation', u'puppy_love.n.01', 'hyp')
(u'worship', u'worship.n.02', 'hyp')
(u'adoration', u'worship.n.02', 'hyp')
(u'adore', u'adore.v.01', 'hyp')
(u'care_for', u'care_for.v.02', 'hyp')
(u'cherish', u'care_for.v.02', 'hyp')
(u'hold_dear', u'care_for.v.02', 'hyp')
(u'treasure', u'care_for.v.02', 'hyp')
(u'dote', u'dote.v.02', 'hyp')
(u'love', u'love.v.03', 'hyp')
(u'get_off', u'get_off.v.06', 'hyp')
(u'romance', u'romance.v.02', 'hyp')
(u'fornicate', u'fornicate.v.01', 'hyp')
(u'take', u'take.v.35', 'hyp')
(u'have', u'take.v.35', 'hyp')
(u'hate', u'hate.n.01', 'ant')
(u'hate', u'hate.v.01', 'ant')
勇敢
(u'brave', u'brave.n.01', 'ss')
(u'brave', u'brave.n.02', 'ss')
(u'weather', u'weather.v.01', 'ss')
(u'endure', u'weather.v.01', 'ss')
(u'brave', u'weather.v.01', 'ss')
(u'brave_out', u'weather.v.01', 'ss')
(u'brave', u'brave.a.01', 'ss')
(u'courageous', u'brave.a.01', 'ss')
(u'audacious', u'audacious.s.01', 'ss')
(u'brave', u'audacious.s.01', 'ss')
(u'dauntless', u'audacious.s.01', 'ss')
(u'fearless', u'audacious.s.01', 'ss')
(u'hardy', u'audacious.s.01', 'ss')
(u'intrepid', u'audacious.s.01', 'ss')
(u'unfearing', u'audacious.s.01', 'ss')
(u'brave', u'brave.s.03', 'ss')
(u'braw', u'brave.s.03', 'ss')
(u'gay', u'brave.s.03', 'ss')
(u'desperate', u'desperate.s.04', 'sim')
(u'heroic', u'desperate.s.04', 'sim')
(u'gallant', u'gallant.s.01', 'sim')
(u'game', u'game.s.02', 'sim')
(u'gamy', u'game.s.02', 'sim')
(u'gamey', u'game.s.02', 'sim')
(u'gritty', u'game.s.02', 'sim')
(u'mettlesome', u'game.s.02', 'sim')
(u'spirited', u'game.s.02', 'sim')
(u'spunky', u'game.s.02', 'sim')
(u'lionhearted', u'lionhearted.s.01', 'sim')
(u'stalwart', u'stalwart.s.03', 'sim')
(u'stouthearted', u'stalwart.s.03', 'sim')
(u'undaunted', u'undaunted.s.02', 'sim')
(u'valiant', u'valiant.s.01', 'sim')
(u'valorous', u'valiant.s.01', 'sim')
(u'bold', u'bold.a.01', 'sim')
(u'colorful', u'colorful.a.02', 'sim')
(u'colourful', u'colorful.a.02', 'sim')
(u'timid', u'timid.n.01', 'ant')
(u'cowardly', u'cowardly.a.01', 'ant')
(u'adventurous', u'adventurous.a.01', 'also')
(u'adventuresome', u'adventurous.a.01', 'also')
(u'bold', u'bold.a.01', 'also')
(u'resolute', u'resolute.a.01', 'also')
(u'unafraid', u'unafraid.a.01', 'also')
(u'fearless', u'unafraid.a.01', 'also')