def tagging(self, text, lower=False):
""" Return the words with POS-tags of the given sentence.
args:
- text (str): An input sentence.
- lower (bool): If lower is True, all uppercase characters in a list \
of the words are converted into lowercase characters.
return:
- object : The object of the words with POS-tags.
"""
words = self.wakati(text, lower)
wids = utils.conv_tokens_to_ids(words, self._word2id)
cids = [
utils.conv_tokens_to_ids([c for c in w.lower()], self._uni2id)
for w in words
]
tids = []
for w in words:
w = w.lower()
if w in self._word2postags:
w2p = self._word2postags[w]
else:
w2p = [0]
if w.isalnum() is True:
if w2p == [0]:
w2p = [self._pos2id[u'名詞']]
else:
w2p.append(self._pos2id[u'名詞'])
w2p = list(set(w2p))
tids.append(w2p)
X = [cids, wids, tids]
postags = [self._id2pos[pid] for pid in self._model.POStagging(X)]
return self._Token(text, words, postags)
def tagging(self, text, lower=False):
"""
Return the words with POS-tags of the given sentence.
Input: str (a sentence)
Output: the object of the words with POS-tags
"""
words = self.wakati(text, lower)
wids = utils.conv_tokens_to_ids(words, self._word2id)
cids = [
utils.conv_tokens_to_ids([c for c in w], self._uni2id)
for w in words
]
tids = []
for w in words:
w = w.lower()
if w in self._word2postags:
w2p = self._word2postags[w]
else:
w2p = [0]
if w.isalnum() is True:
if w2p == [0]:
w2p = [self._pos2id[u'名詞']]
else:
w2p.append(self._pos2id[u'名詞'])
w2p = list(set(w2p))
tids.append(w2p)
X = [cids, wids, tids]
postags = [self._id2pos[pid] for pid in self._model.POStagging(X)]
return self._Token(text, words, postags)
def _postagging(self, words, lower=False):
if lower is True:
words = [w.lower() for w in words]
wids = utils.conv_tokens_to_ids(words, self._word2id)
cids = [
utils.conv_tokens_to_ids([c for c in w], self._uni2id)
for w in words
]
tids = []
for w in words:
if w in self._word2postags:
w2p = self._word2postags[w]
else:
w2p = [0]
if self.use_noun_heuristic is True:
if w.isalnum() is True:
if w2p == [0]:
w2p = [self._pos2id[u'名詞']]
else:
w2p.append(self._pos2id[u'名詞'])
w2p = list(set(w2p))
tids.append(w2p)
X = [cids, wids, tids]
postags = [self._id2pos[pid] for pid in self._model.POStagging(X)]
return postags