-
Notifications
You must be signed in to change notification settings - Fork 14
/
nltk_processors.py
336 lines (280 loc) · 11.8 KB
/
nltk_processors.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
# Copyright 2021 The Forte Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from typing import List, Dict, Set
from forte.common.configuration import Config
from forte.common.resources import Resources
from forte.data.data_pack import DataPack
from forte.processors.base import PackProcessor
from ft.onto.base_ontology import EntityMention, Token, Sentence, Phrase
from nltk import ( # type: ignore
pos_tag,
ne_chunk,
PunktSentenceTokenizer,
download,
)
from nltk.chunk import RegexpParser
from nltk.stem import WordNetLemmatizer
from nltk.tokenize.treebank import TreebankWordTokenizer
__all__ = [
"NLTKPOSTagger",
"NLTKSentenceSegmenter",
"NLTKWordTokenizer",
"NLTKLemmatizer",
"NLTKChunker",
"NLTKNER",
]
class NLTKWordTokenizer(PackProcessor):
r"""A wrapper of NLTK word tokenizer."""
def __init__(self):
super().__init__()
self.tokenizer = TreebankWordTokenizer()
def _process(self, input_pack: DataPack):
for begin, end in self.tokenizer.span_tokenize(input_pack.text):
Token(input_pack, begin, end)
def record(self, record_meta: Dict[str, Set[str]]):
r"""Method to add output type record of `NLTKWordTokenizer`, which is
`ft.onto.base_ontology.Token`,
to :attr:`forte.data.data_pack.Meta.record`.
Args:
record_meta: the field in the datapack for type record that need to
fill in for consistency checking.
"""
record_meta["ft.onto.base_ontology.Token"] = set()
class NLTKPOSTagger(PackProcessor):
r"""A wrapper of NLTK pos tagger."""
def initialize(self, resources: Resources, configs: Config):
super().initialize(resources, configs)
download("averaged_perceptron_tagger")
def __init__(self):
super().__init__()
self.token_component = None
def _process(self, input_pack: DataPack):
token_entries = list(
input_pack.get(entry_type=Token, components=self.token_component)
)
token_texts = [token.text for token in token_entries]
taggings = pos_tag(token_texts)
for token, tag in zip(token_entries, taggings):
token.pos = tag[1]
def record(self, record_meta: Dict[str, Set[str]]):
r"""Method to add output type record of `NLTKPOSTagger`, which adds
attribute `pos` to `ft.onto.base_ontology.Token`
to :attr:`forte.data.data_pack.Meta.record`.
Args:
record_meta: the field in the datapack for type record that need to
fill in for consistency checking.
"""
record_meta["ft.onto.base_ontology.Token"].add("pos")
def expected_types_and_attributes(self):
r"""Method to add expected type `ft.onto.base_ontology.Token` for input
which would be checked before running the processor if
the pipeline is initialized with
`enforce_consistency=True` or
:meth:`~forte.pipeline.Pipeline.enforce_consistency` was enabled for
the pipeline.
"""
return {"ft.onto.base_ontology.Token": set()}
class NLTKLemmatizer(PackProcessor):
r"""A wrapper of NLTK lemmatizer."""
def initialize(self, resources: Resources, configs: Config):
super().initialize(resources, configs)
download("wordnet")
def __init__(self):
super().__init__()
self.token_component = None
self.lemmatizer = WordNetLemmatizer()
def _process(self, input_pack: DataPack):
token_entries: List[Token] = list(
input_pack.get(entry_type=Token, components=self.token_component)
)
token_texts: List[str] = []
token_poses: List[str] = []
for token in token_entries:
token_texts.append(token.text)
assert token.pos is not None
token_poses.append(penn2morphy(token.pos))
lemmas = [
self.lemmatizer.lemmatize(token_texts[i], token_poses[i])
for i in range(len(token_texts))
]
for token, lemma in zip(token_entries, lemmas):
token.lemma = lemma
def record(self, record_meta: Dict[str, Set[str]]):
r"""Method to add output type record of `NLTKLemmatizer` which adds
attribute `lemma` to `ft.onto.base_ontology.Token`
to :attr:`forte.data.data_pack.Meta.record`.
Args:
record_meta: the field in the datapack for type record that need to
fill in for consistency checking.
"""
record_meta["ft.onto.base_ontology.Token"].add("lemma")
def expected_types_and_attributes(self):
r"""Method to add expected type `ft.onto.base_ontology.Token` with
attribute `pos` which
would be checked before running the processor if
the pipeline is initialized with
`enforce_consistency=True` or
:meth:`~forte.pipeline.Pipeline.enforce_consistency` was enabled for
the pipeline.
"""
return {"ft.onto.base_ontology.Token": {"pos"}}
def penn2morphy(penntag: str) -> str:
r"""Converts tags from Penn format to Morphy."""
morphy_tag = {"NN": "n", "JJ": "a", "VB": "v", "RB": "r"}
if penntag[:2] in morphy_tag:
return morphy_tag[penntag[:2]]
else:
return "n"
class NLTKChunker(PackProcessor):
r"""A wrapper of NLTK chunker."""
def __init__(self):
super().__init__()
self.chunker = None
def initialize(self, resources: Resources, configs: Config):
super().initialize(resources, configs)
download("maxent_ne_chunker")
self.chunker = RegexpParser(configs.pattern)
@classmethod
def default_configs(cls):
r"""This defines a basic config structure for NLTKChunker."""
return {
"pattern": "NP: {<DT>?<JJ>*<NN>}",
"token_component": None,
"sentence_component": None,
}
def _process(self, input_pack: DataPack):
for sentence in input_pack.get(
Sentence, components=self.configs.sentence_component
):
token_entries = list(
input_pack.get(
entry_type=Token,
range_annotation=sentence,
components=self.configs.token_component,
)
)
tokens = [(token.text, token.pos) for token in token_entries]
cs = self.chunker.parse(tokens)
index = 0
for chunk in cs:
if hasattr(chunk, "label"):
# For example:
# chunk: Tree('NP', [('This', 'DT'), ('tool', 'NN')])
begin_pos = token_entries[index].span.begin
end_pos = token_entries[index + len(chunk) - 1].span.end
phrase = Phrase(input_pack, begin_pos, end_pos)
phrase.phrase_type = chunk.label()
index += len(chunk)
else:
# For example:
# chunk: ('is', 'VBZ')
index += 1
def record(self, record_meta: Dict[str, Set[str]]):
r"""Method to add output type record of `NLTKChunker` which adds
`ft.onto.base_ontology.Phrase` with attribute `phrase_type`
to :attr:`forte.data.data_pack.Meta.record`.
Args:
record_meta: the field in the datapack for type record that need to
fill in for consistency checking.
"""
record_meta["ft.onto.base_ontology.Phrase"] = {"phrase_type"}
def expected_types_and_attributes(self):
r"""Method to add expected type ft.onto.base_ontology.Token` with
attribute `pos` and `ft.onto.base_ontology.Sentence` which
would be checked before running the processor if
the pipeline is initialized with
`enforce_consistency=True` or
:meth:`~forte.pipeline.Pipeline.enforce_consistency` was enabled for
the pipeline.
"""
return {
"ft.onto.base_ontology.Sentence": set(),
"ft.onto.base_ontology.Token": {"pos"},
}
class NLTKSentenceSegmenter(PackProcessor):
r"""A wrapper of NLTK sentence tokenizer."""
def initialize(self, resources: Resources, configs: Config):
super().initialize(resources, configs)
download("punkt")
def __init__(self):
super().__init__()
self.sent_splitter = PunktSentenceTokenizer()
def _process(self, input_pack: DataPack):
for begin, end in self.sent_splitter.span_tokenize(input_pack.text):
Sentence(input_pack, begin, end)
def record(self, record_meta: Dict[str, Set[str]]):
r"""Method to add output type record of `NLTKSentenceSegmenter`, which
is `ft.onto.base_ontology.Sentence`
to :attr:`forte.data.data_pack.Meta.record`.
Args:
record_meta: the field in the datapack for type record that need to
fill in for consistency checking.
"""
record_meta["ft.onto.base_ontology.Sentence"] = set()
class NLTKNER(PackProcessor):
r"""A wrapper of NLTK NER."""
def initialize(self, resources: Resources, configs: Config):
super().initialize(resources, configs)
download("maxent_ne_chunker")
download("words")
def __init__(self):
super().__init__()
self.token_component = None
def _process(self, input_pack: DataPack):
for sentence in input_pack.get(Sentence):
token_entries = list(
input_pack.get(
entry_type=Token,
range_annotation=sentence,
components=self.token_component,
)
)
tokens = [(token.text, token.pos) for token in token_entries]
ne_tree = ne_chunk(tokens)
index = 0
for chunk in ne_tree:
if hasattr(chunk, "label"):
# For example:
# chunk: Tree('GPE', [('New', 'NNP'), ('York', 'NNP')])
begin_pos = token_entries[index].span.begin
end_pos = token_entries[index + len(chunk) - 1].span.end
entity = EntityMention(input_pack, begin_pos, end_pos)
entity.ner_type = chunk.label()
index += len(chunk)
else:
# For example:
# chunk: ('This', 'DT')
index += 1
def record(self, record_meta: Dict[str, Set[str]]):
r"""Method to add output type record of `NLTKNER` which is
`ft.onto.base_ontology.EntityMention` with attribute `phrase_type`
to :attr:`forte.data.data_pack.Meta.record`.
Args:
record_meta: the field in the datapack for type record that need to
fill in for consistency checking.
"""
record_meta["ft.onto.base_ontology.EntityMention"] = {"ner_type"}
def expected_types_and_attributes(self):
r"""Method to add expected type ft.onto.base_ontology.Token` with
attribute `pos` and `ft.onto.base_ontology.Sentence` which
would be checked before running the processor if
the pipeline is initialized with
`enforce_consistency=True` or
:meth:`~forte.pipeline.Pipeline.enforce_consistency` was enabled for
the pipeline.
"""
return {
"ft.onto.base_ontology.Sentence": set(),
"ft.onto.base_ontology.Token": {"pos"},
}