Spaces:
Restarting
Restarting
File size: 13,397 Bytes
efbe6b4 686f61c efbe6b4 15355ff |
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 |
import copy
import string
from random import random
from random import sample
from utilities_language_general.rus_constants import nlp
from utilities_language_general.rus_utils import get_tags
from utilities_language_general.rus_constants import PHRASES
from utilities_language_general.rus_utils import define_gender
from utilities_language_general.rus_utils import make_inflection
from utilities_language_general.rus_utils import check_token_bert
from utilities_language_general.rus_constants import BAD_USER_TARGET_WORDS
from utilities_language_general.rus_utils import get_distractors_from_model_bert
class SENTENCE:
def __init__(self, original: str, n_sentence: int, max_num_distractors):
self.original = original
self.n_sentence = n_sentence
self.max_num_distractors = max_num_distractors
self.parsed = nlp(self.original)
self.sentence_lemma_pos = []
self.sentence_phrases = []
self.target_words = []
self.text_with_masked_task = ''
def lemmatize_sentence(self):
for token in self.parsed:
lemma_pos = f'{token.lemma_}_{token.pos_}'
self.sentence_lemma_pos.append((lemma_pos, token))
def bind_phrases(self):
previous_was_phrase = False
for i in range(len(self.sentence_lemma_pos) - 1):
phrase_candidate = f'{self.sentence_lemma_pos[i][0]}_{self.sentence_lemma_pos[i + 1][0]}'
if phrase_candidate in PHRASES and not previous_was_phrase:
# phrase is {phrase: {original_token1: spacy.token, original_token2: spacy.token}}
phrase = [
f'{self.sentence_lemma_pos[i][0]}_{self.sentence_lemma_pos[i + 1][0]}',
{
'original_token1': self.sentence_lemma_pos[i][1],
'original_token2': self.sentence_lemma_pos[i + 1][1]
}
]
self.sentence_phrases.append(phrase)
previous_was_phrase = True
else:
if not previous_was_phrase:
self.sentence_phrases.append(self.sentence_lemma_pos[i][1])
previous_was_phrase = False
def search_target_words_automatically(self, target_minimum: set, frequency_dict: dict = None):
for token in self.sentence_phrases:
# TODO: Still do not have w2v model with phrases
# therefore cannot come up with the criteria
if isinstance(token, list): # if token is a phrase
original_token1 = token[1]['original_token1']
original_token2 = token[1]['original_token2']
original_token1_tags = get_tags(original_token1.text)[0]
original_token2_tags = get_tags(original_token2.text)[0]
tags = original_token1_tags | original_token2_tags
not_ner = True if (original_token1.ent_type == 0 and original_token2.ent_type == 0) else False
target_word = {
'masked_sentence': self.original.replace(f'{original_token1.text} {original_token2.text}',
'[MASK]'),
'sentence_number': self.n_sentence,
'sentence_text': self.original,
'original_text': f'{original_token1.text} {original_token2.text}',
'lemma': token[0],
'pos': ('phrase', [original_token1.pos_, original_token2.pos_]),
'gender': list({define_gender(original_token1), define_gender(original_token2)})[0],
'tags': tags,
'position_in_sentence': self.original.find(original_token1.text),
'not_named_entity': not_ner,
'frequency_in_text': 0
}
self.target_words.append(target_word)
else: # if token is just a spacy.nlp token
if check_token_bert(token=token, current_minimum=target_minimum):
target_word = {
'masked_sentence': self.original.replace(token.text, '[MASK]'),
'sentence_number': self.n_sentence,
'sentence_text': self.original,
'original_text': token.text,
'lemma': token.lemma_,
'pos': ('simple', token.pos_),
'gender': define_gender(token.lemma_),
'number_children': len([child for child in token.children]),
'tags': get_tags(token.text)[0],
'position_in_sentence': self.original.find(token.text),
'not_named_entity': True if token.ent_type == 0 else False,
'frequency_in_text': frequency_dict.get(token.lemma_, 1),
}
self.target_words.append(target_word)
def search_user_target_words(self, user_target_words: set = None, frequency_dict: dict = None):
for _utw in user_target_words:
if _utw in self.original:
parse_utw = nlp(_utw)
if ' ' in _utw:
tags = get_tags(parse_utw[0].text)[0] | get_tags(parse_utw[1].text)[0]
user_target_word_lemma = '_'.join([f'{token.lemma_}_{token.pos_}' for token in parse_utw])
user_target_word_pos = ('phrase', [token.pos_ for token in parse_utw])
user_target_word_tags = tags
not_ner = True if (parse_utw[0].ent_type == 0 and parse_utw[1].ent_type == 0) else False
else:
user_target_word_lemma = f'{parse_utw[0].lemma_}_{parse_utw[0].pos_}'
user_target_word_pos = ('simple', parse_utw[0].pos_)
user_target_word_tags = get_tags(parse_utw[0].text)[0]
not_ner = parse_utw[0].ent_type == 0
target_word = {
'masked_sentence': self.original.replace(_utw, '[MASK]'),
'sentence_number': self.n_sentence,
'sentence_text': self.original,
'original_text': _utw,
'lemma': user_target_word_lemma,
'pos': user_target_word_pos,
'gender': define_gender(parse_utw[0].text),
'tags': user_target_word_tags,
'position_in_sentence': self.original.find(_utw),
'not_named_entity': not_ner,
'frequency_in_text': frequency_dict.get(user_target_word_lemma, 1)
}
self.target_words.append(target_word)
def search_target_words(self, target_words_automatic_mode: bool, target_minimum,
user_target_words: set = None,
frequency_dict: dict = None):
if target_words_automatic_mode:
self.search_target_words_automatically(target_minimum=target_minimum,
frequency_dict=frequency_dict)
else:
self.search_user_target_words(user_target_words=user_target_words,
frequency_dict=frequency_dict)
def filter_target_words(self, target_words_automatic_mode):
c_position = 0
bad_target_words = []
for target_word in self.target_words:
position_difference = 3 if target_words_automatic_mode else 0
if not (target_word['position_in_sentence'] == 0
or abs(target_word['position_in_sentence'] - c_position) >= position_difference):
bad_target_words.append(target_word)
for btw in bad_target_words:
BAD_USER_TARGET_WORDS.append(btw['original_text'])
self.target_words.remove(btw)
class TASK:
def __init__(self, task_data, max_num_distractors):
self.task_data = task_data
self.distractors = None
self.distractors_number = 0
self.bad_target_word = False
self.inflected_distractors = None
self.pos = task_data['pos']
self.tags = task_data['tags']
self.lemma = task_data['lemma']
self.gender = task_data['gender']
self.max_num_distractors = max_num_distractors
self.original_text = task_data['original_text']
self.sentence_text = task_data['sentence_text']
self.sentence_number = task_data['sentence_number']
self.masked_sentence = task_data['masked_sentence']
self.frequency_in_text = task_data['frequency_in_text']
self.position_in_sentence = task_data['position_in_sentence']
self.text_with_masked_task = task_data['text_with_masked_task']
self.result = ''
self.variants = []
def __repr__(self):
return '\n'.join([f'{key}\t=\t{value}' for key, value in self.__dict__.items()])
def attach_distractors_to_target_word(self, model, global_distractors, distractor_minimum,
level_name, max_frequency):
pos = self.pos[0] if self.pos[0] == 'phrase' else self.pos[1]
# distractors_full_text = get_distractors_from_model_bert(model=model, lemma=self.lemma, pos=pos,
# gender=self.gender, level_name=level_name,
# text_with_masked_task=self.text_with_masked_task,
# global_distractors=global_distractors,
# distractor_minimum=distractor_minimum,
# max_num_distractors=self.max_num_distractors)
distractors_sentence = get_distractors_from_model_bert(model=model, lemma=self.lemma, pos=pos,
gender=self.gender, level_name=level_name,
text_with_masked_task=self.masked_sentence,
global_distractors=global_distractors,
distractor_minimum=distractor_minimum,
max_num_distractors=self.max_num_distractors)
if distractors_sentence is None or self.frequency_in_text > max_frequency:
self.bad_target_word = True
self.distractors = None
else:
self.distractors = [d[0] for i, d in enumerate(distractors_sentence) if i < 15]
self.distractors_number = len(distractors_sentence) if distractors_sentence is not None else 0
def inflect_distractors(self):
inflected_distractors = []
if self.distractors is None:
self.bad_target_word = True
return
for distractor_lemma in self.distractors:
inflected = make_inflection(text=distractor_lemma, pos=self.pos[1], tags=self.tags)
if inflected is not None:
inflected_distractors.append(inflected)
else:
new_tags = copy.deepcopy(self.tags)
if 'NOUN' in self.tags and 'inan' in self.tags:
new_tags.discard('inan')
new_tags.add('anim')
elif 'NOUN' in self.tags and 'anim' in self.tags:
new_tags.discard('anim')
new_tags.add('inan')
inflected = make_inflection(text=distractor_lemma, pos=self.pos[1], tags=new_tags)
if inflected is not None:
inflected_distractors.append(inflected)
num_distractors = min(4, self.max_num_distractors) if self.max_num_distractors >= 4 \
else self.max_num_distractors
if len(inflected_distractors) < num_distractors:
self.bad_target_word = True
else:
self.distractors_number = num_distractors
self.inflected_distractors = inflected_distractors
def sample_distractors(self, num_distractors):
if not self.bad_target_word:
num_distractors = min(self.distractors_number, num_distractors) \
if num_distractors >= 4 else num_distractors
self.inflected_distractors = sample(self.inflected_distractors[:min(self.distractors_number, 10)],
num_distractors)
def compile_task(self, max_num_distractors):
len_distractors = len(self.inflected_distractors)
len_variants = min(len_distractors, max_num_distractors) if max_num_distractors > 4 \
else max_num_distractors
letters = (f'({letter})' for letter in string.ascii_lowercase[:len_variants + 1])
try:
distractors = sample(self.inflected_distractors, len_variants) + [self.original_text, ]
except ValueError:
distractors = self.inflected_distractors + [self.original_text, ]
tmp_vars = [f'{item[0]} {item[1].replace("_", " ").lower()}'.lower()
for item in zip(letters, sorted(distractors, key=lambda _: random()))]
self.variants.append((self.original_text.lower(), tmp_vars))
|