def _slot_matching_lambda(lhs_slot, rhs_slot):
lhs_value = lhs_slot["text"]
rhs_value = rhs_slot["rawValue"]
if lhs_slot["entity"] != "snips/datetime":
return lhs_value == rhs_value
else:
# Allow fuzzy matching when comparing datetimes
lhs_tokens = tokenize_light(lhs_value, LANGUAGE_EN)
rhs_tokens = tokenize_light(rhs_value, LANGUAGE_EN)
if lhs_tokens and lhs_tokens[0].lower() in SKIPPED_DATE_PREFIXES:
lhs_tokens = lhs_tokens[1:]
if rhs_tokens and rhs_tokens[0].lower() in SKIPPED_DATE_PREFIXES:
rhs_tokens = rhs_tokens[1:]
return lhs_tokens == rhs_tokens
def generate_noise_utterances(augmented_utterances, noise, num_intents,
data_augmentation_config, language,
random_state):
if not augmented_utterances or not num_intents:
return []
avg_num_utterances = len(augmented_utterances) / float(num_intents)
if data_augmentation_config.unknown_words_replacement_string is not None:
noise = generate_smart_noise(
noise, augmented_utterances,
data_augmentation_config.unknown_words_replacement_string,
language)
noise_size = min(
int(data_augmentation_config.noise_factor * avg_num_utterances),
len(noise))
utterances_lengths = [
len(tokenize_light(get_text_from_chunks(u[DATA]), language))
for u in augmented_utterances
]
mean_utterances_length = np.mean(utterances_lengths)
std_utterances_length = np.std(utterances_lengths)
noise_it = get_noise_it(noise, mean_utterances_length,
std_utterances_length, random_state)
# Remove duplicate 'unknownword unknownword'
return [
text_to_utterance(UNKNOWNWORD_REGEX.sub(UNKNOWNWORD, next(noise_it)))
for _ in range(noise_size)
]
def _utterance_to_pattern(self, utterance, stop_words,
entity_placeholders):
from snips_nlu_utils import normalize
slot_names_count = defaultdict(int)
pattern = []
for chunk in utterance[DATA]:
if SLOT_NAME in chunk:
slot_name = chunk[SLOT_NAME]
slot_names_count[slot_name] += 1
group_name = self.slot_names_to_group_names[slot_name]
count = slot_names_count[slot_name]
if count > 1:
group_name = "%s_%s" % (group_name, count)
placeholder = entity_placeholders[chunk[ENTITY]]
pattern.append(r"(?P<%s>%s)" % (group_name, placeholder))
else:
tokens = tokenize_light(chunk[TEXT], self.language)
pattern += [
regex_escape(t.lower()) for t in tokens
if normalize(t) not in stop_words
]
pattern = r"^%s%s%s$" % (WHITESPACE_PATTERN,
WHITESPACE_PATTERN.join(pattern),
WHITESPACE_PATTERN)
return pattern
def _init_vectorizer(self, language):
from sklearn.feature_extraction.text import (TfidfVectorizer as
SklearnTfidfVectorizer)
self._tfidf_vectorizer = SklearnTfidfVectorizer(
tokenizer=lambda x: tokenize_light(x, language))
return self
def generate_smart_noise(noise, augmented_utterances, replacement_string,
language):
text_utterances = [get_text_from_chunks(u[DATA])
for u in augmented_utterances]
vocab = [w for u in text_utterances for w in tokenize_light(u, language)]
vocab = set(vocab)
return [w if w in vocab else replacement_string for w in noise]
def _preprocess_text(self, txt, intent):
"""Replaces stop words and characters that are tokenized out by
whitespaces"""
stop_words = self._get_intent_stop_words(intent)
tokens = tokenize_light(txt, self.language)
cleaned_string = " ".join(
[tkn for tkn in tokens if normalize(tkn) not in stop_words])
return cleaned_string.lower()
def fit(self, dataset, utterances, classes):
utterances_texts = (get_text_from_chunks(u[DATA]) for u in utterances)
if not any(tokenize_light(q, self.language) for q in utterances_texts):
return None
utterances_to_features = _get_utterances_to_features_names(
dataset, self.language)
normalized_utterances_to_features = defaultdict(set)
for k, v in iteritems(utterances_to_features):
normalized_utterances_to_features[_normalize_stem(
k, self.language)].update(v)
if self.unknown_words_replacement_string is not None \
and self.unknown_words_replacement_string in \
normalized_utterances_to_features:
normalized_utterances_to_features.pop(
self.unknown_words_replacement_string)
self.entity_utterances_to_feature_names = dict(
normalized_utterances_to_features)
preprocessed_utterances = self.preprocess_utterances(utterances)
# pylint: disable=C0103
X_train_tfidf = self.tfidf_vectorizer.fit_transform(
preprocessed_utterances)
# pylint: enable=C0103
features_idx = {
self.tfidf_vectorizer.vocabulary_[word]: word
for word in self.tfidf_vectorizer.vocabulary_
}
stop_words = get_stop_words(self.language)
_, pval = chi2(X_train_tfidf, classes)
self.best_features = [
i for i, v in enumerate(pval) if v < self.config.pvalue_threshold
]
if not self.best_features:
self.best_features = [
idx for idx, val in enumerate(pval) if val == pval.min()
]
feature_names = {}
for utterance_index in self.best_features:
feature_names[utterance_index] = {
"word": features_idx[utterance_index],
"pval": pval[utterance_index]
}
for feat in feature_names:
if feature_names[feat]["word"] in stop_words:
if feature_names[feat]["pval"] > \
self.config.pvalue_threshold / 2.0:
self.best_features.remove(feat)
return self
def _enrich_utterance(self, x, builtin_ents, custom_ents):
utterance = get_text_from_chunks(x[DATA])
all_entities = builtin_ents + custom_ents
placeholder_fn = self._placeholder_fn
# Replace entities with placeholders
enriched_utterance = replace_entities_with_placeholders(
utterance, all_entities, placeholder_fn)[1]
# Tokenize
enriched_utterance = tokenize_light(enriched_utterance, self.language)
# Remove the unknownword strings if needed
if self.config.unknown_words_replacement_string:
enriched_utterance = [
t for t in enriched_utterance
if t != self.config.unknown_words_replacement_string
]
return enriched_utterance
def from_path(cls, path, **shared):
import numpy as np
import scipy.sparse as sp
from sklearn.feature_extraction.text import (TfidfTransformer,
TfidfVectorizer as
SklearnTfidfVectorizer)
path = Path(path)
model_path = path / "vectorizer.json"
if not model_path.exists():
raise LoadingError("Missing vectorizer model file: %s" %
model_path.name)
with model_path.open("r", encoding="utf-8") as f:
vectorizer_dict = json.load(f)
vectorizer = cls(vectorizer_dict["config"], **shared)
vectorizer._language = vectorizer_dict["language_code"]
builtin_entity_scope = vectorizer_dict["builtin_entity_scope"]
if builtin_entity_scope is not None:
builtin_entity_scope = set(builtin_entity_scope)
vectorizer.builtin_entity_scope = builtin_entity_scope
vectorizer_ = vectorizer_dict["vectorizer"]
if vectorizer_:
vocab = vectorizer_["vocab"]
idf_diag_data = vectorizer_["idf_diag"]
idf_diag_data = np.array(idf_diag_data)
idf_diag_shape = (len(idf_diag_data), len(idf_diag_data))
row = list(range(idf_diag_shape[0]))
col = list(range(idf_diag_shape[0]))
idf_diag = sp.csr_matrix((idf_diag_data, (row, col)),
shape=idf_diag_shape)
tfidf_transformer = TfidfTransformer()
tfidf_transformer._idf_diag = idf_diag
vectorizer_ = SklearnTfidfVectorizer(
tokenizer=lambda x: tokenize_light(x, vectorizer._language))
vectorizer_.vocabulary_ = vocab
vectorizer_._tfidf = tfidf_transformer
vectorizer._tfidf_vectorizer = vectorizer_
return vectorizer
def _create_custom_entity_parser_configuration(
entities, stopwords_fraction, language):
"""Dynamically creates the gazetteer parser configuration.
Args:
entities (dict): entity for the dataset
stopwords_fraction (float): fraction of the vocabulary of
the entity values that will be considered as stop words (
the top n_vocabulary * stopwords_fraction most frequent words will
be considered stop words)
language (str): language of the entities
Returns: the parser configuration as dictionary
"""
if not 0 < stopwords_fraction < 1:
raise ValueError("stopwords_fraction must be in ]0.0, 1.0[")
parser_configurations = []
for entity_name, entity in sorted(iteritems(entities)):
vocabulary = set(
t for raw_value in entity[UTTERANCES]
for t in tokenize_light(raw_value, language)
)
num_stopwords = int(stopwords_fraction * len(vocabulary))
config = {
"entity_identifier": entity_name,
"entity_parser": {
"threshold": entity[MATCHING_STRICTNESS],
"n_gazetteer_stop_words": num_stopwords,
"gazetteer": [
{
"raw_value": k,
"resolved_value": v
} for k, v in sorted(iteritems(entity[UTTERANCES]))
]
}
}
if LICENSE_INFO in entity:
config["entity_parser"][LICENSE_INFO] = entity[LICENSE_INFO]
parser_configurations.append(config)
configuration = {
"entity_parsers": parser_configurations
}
return configuration
def _query_to_pattern(query, joined_entity_utterances,
group_names_to_slot_names, language):
pattern = []
for chunk in query[DATA]:
if SLOT_NAME in chunk:
max_index = _generate_new_index(group_names_to_slot_names)
slot_name = chunk[SLOT_NAME]
entity = chunk[ENTITY]
group_names_to_slot_names[max_index] = slot_name
pattern.append(
r"(?P<%s>%s)" % (max_index, joined_entity_utterances[entity]))
else:
tokens = tokenize_light(chunk[TEXT], language)
pattern += [regex_escape(t) for t in tokens]
pattern = r"^%s%s%s$" % (WHITESPACE_PATTERN,
WHITESPACE_PATTERN.join(pattern),
WHITESPACE_PATTERN)
return pattern, group_names_to_slot_names
def fit_transform(self, dataset, utterances, classes, none_class):
dataset = validate_and_format_dataset(dataset)
self.language = dataset[LANGUAGE]
utterances_texts = (get_text_from_chunks(u[DATA]) for u in utterances)
if not any(tokenize_light(q, self.language) for q in utterances_texts):
raise _EmptyDatasetUtterancesError(
"Tokenized utterances are empty")
x_tfidf = self._fit_transform_tfidf_vectorizer(utterances, classes,
dataset)
x = x_tfidf
if self.config.added_cooccurrence_feature_ratio:
self._fit_cooccurrence_vectorizer(utterances, classes, none_class,
dataset)
x_cooccurrence = self.cooccurrence_vectorizer.transform(utterances)
x = sp.hstack((x_tfidf, x_cooccurrence))
return x
def _preprocess_utterance(utterance, language, builtin_entity_parser,
custom_entity_parser, word_clusters_name,
use_stemming, unknownword_replacement_string):
utterance_text = get_text_from_chunks(utterance[DATA])
utterance_tokens = tokenize_light(utterance_text, language)
word_clusters_features = _get_word_cluster_features(
utterance_tokens, word_clusters_name, language)
normalized_stemmed_tokens = [_normalize_stem(t, language, use_stemming)
for t in utterance_tokens]
custom_entities = custom_entity_parser.parse(
" ".join(normalized_stemmed_tokens))
custom_entities = [e for e in custom_entities
if e["value"] != unknownword_replacement_string]
custom_entities_features = [
_entity_name_to_feature(e[ENTITY_KIND], language)
for e in custom_entities]
builtin_entities = builtin_entity_parser.parse(
utterance_text, use_cache=True)
builtin_entities_features = [
_builtin_entity_to_feature(ent[ENTITY_KIND], language)
for ent in builtin_entities
]
# We remove values of builtin slots from the utterance to avoid learning
# specific samples such as '42' or 'tomorrow'
filtered_normalized_stemmed_tokens = [
_normalize_stem(chunk[TEXT], language, use_stemming)
for chunk in utterance[DATA]
if ENTITY not in chunk or not is_builtin_entity(chunk[ENTITY])
]
features = get_default_sep(language).join(
filtered_normalized_stemmed_tokens)
if builtin_entities_features:
features += " " + " ".join(sorted(builtin_entities_features))
if custom_entities_features:
features += " " + " ".join(sorted(custom_entities_features))
if word_clusters_features:
features += " " + " ".join(sorted(word_clusters_features))
return features
def _get_joined_entity_utterances(dataset, language):
joined_entity_utterances = dict()
for entity_name, entity in iteritems(dataset[ENTITIES]):
# matches are performed in a case insensitive manner
utterances = set(u.lower() for u in entity[UTTERANCES])
patterns = []
if is_builtin_entity(entity_name):
# We add a placeholder value for builtin entities
placeholder = _get_entity_name_placeholder(entity_name, language)
patterns.append(regex_escape(placeholder))
else:
for utterance in utterances:
tokens = tokenize_light(utterance, language)
pattern = WHITESPACE_PATTERN.join(regex_escape(t)
for t in tokens)
patterns.append(pattern)
patterns = (p for p in patterns if p)
joined_entity_utterances[entity_name] = r"|".join(
sorted(patterns, key=len, reverse=True))
return joined_entity_utterances
def get_string_variations(string, language):
variations = {string}
variations.update(flatten(case_variations(v) for v in variations))
variations.update(flatten(normalization_variations(v) for v in variations))
# We re-generate case variations as normalization can produce new
# variations
variations.update(flatten(case_variations(v) for v in variations))
variations.update(flatten(and_variations(v, language) for v in variations))
variations.update(
flatten(punctuation_variations(v, language) for v in variations))
variations.update(
flatten(numbers_variations(v, language) for v in variations))
# Add single space variations
single_space_variations = set(" ".join(v.split()) for v in variations)
variations.update(single_space_variations)
# Add tokenized variations
tokenized_variations = set(
get_default_sep(language).join(tokenize_light(v, language))
for v in variations)
variations.update(tokenized_variations)
return variations
def _preprocess(self, utterances, training=False):
normalized_utterances = deepcopy(utterances)
for u in normalized_utterances:
for chunk in u[DATA]:
chunk[TEXT] = _normalize_stem(chunk[TEXT], self.language,
self.resources,
self.config.use_stemming)
if training:
builtin_ents, custom_ents = zip(
*[_entities_from_utterance(u) for u in utterances])
else:
# Extract builtin entities on unormalized utterances
builtin_ents = [
self.builtin_entity_parser.parse(get_text_from_chunks(u[DATA]),
self.builtin_entity_scope,
use_cache=True)
for u in utterances
]
# Extract builtin entities on normalized utterances
custom_ents = [
self.custom_entity_parser.parse(get_text_from_chunks(u[DATA]),
use_cache=True)
for u in normalized_utterances
]
if self.config.word_clusters_name:
# Extract world clusters on unormalized utterances
original_utterances_text = [
get_text_from_chunks(u[DATA]) for u in utterances
]
w_clusters = [
_get_word_cluster_features(
tokenize_light(u.lower(), self.language),
self.config.word_clusters_name, self.resources)
for u in original_utterances_text
]
else:
w_clusters = [None for _ in normalized_utterances]
return normalized_utterances, builtin_ents, custom_ents, w_clusters
def fit(self, dataset, utterances, classes):
self.fit_builtin_entity_parser_if_needed(dataset)
self.fit_custom_entity_parser_if_needed(dataset)
utterances_texts = (get_text_from_chunks(u[DATA]) for u in utterances)
if not any(tokenize_light(q, self.language) for q in utterances_texts):
return None
preprocessed_utterances = self.preprocess_utterances(utterances)
# pylint: disable=C0103
X_train_tfidf = self.tfidf_vectorizer.fit_transform(
preprocessed_utterances)
# pylint: enable=C0103
features_idx = {self.tfidf_vectorizer.vocabulary_[word]: word for word
in self.tfidf_vectorizer.vocabulary_}
stop_words = get_stop_words(self.language)
_, pval = chi2(X_train_tfidf, classes)
self.best_features = [i for i, v in enumerate(pval) if
v < self.config.pvalue_threshold]
if not self.best_features:
self.best_features = [idx for idx, val in enumerate(pval) if
val == pval.min()]
feature_names = {}
for utterance_index in self.best_features:
feature_names[utterance_index] = {
"word": features_idx[utterance_index],
"pval": pval[utterance_index]}
for feat in feature_names:
if feature_names[feat]["word"] in stop_words:
if feature_names[feat]["pval"] > \
self.config.pvalue_threshold / 2.0:
self.best_features.remove(feat)
return self
def _preprocess_utterance(utterance, language,
entity_utterances_to_features_names,
word_clusters_name):
utterance_text = get_text_from_chunks(utterance[DATA])
utterance_tokens = tokenize_light(utterance_text, language)
word_clusters_features = _get_word_cluster_features(
utterance_tokens, word_clusters_name, language)
normalized_stemmed_tokens = [
_normalize_stem(t, language) for t in utterance_tokens
]
entities_features = _get_dataset_entities_features(
normalized_stemmed_tokens, entity_utterances_to_features_names)
builtin_entities = get_builtin_entities(utterance_text,
language,
use_cache=True)
builtin_entities_features = [
_builtin_entity_to_feature(ent[ENTITY_KIND], language)
for ent in builtin_entities
]
# We remove values of builtin slots from the utterance to avoid learning
# specific samples such as '42' or 'tomorrow'
filtered_normalized_stemmed_tokens = [
_normalize_stem(chunk[TEXT], language) for chunk in utterance[DATA]
if ENTITY not in chunk or not is_builtin_entity(chunk[ENTITY])
]
features = get_default_sep(language).join(
filtered_normalized_stemmed_tokens)
if builtin_entities_features:
features += " " + " ".join(sorted(builtin_entities_features))
if entities_features:
features += " " + " ".join(sorted(entities_features))
if word_clusters_features:
features += " " + " ".join(sorted(word_clusters_features))
return features
def _builtin_entity_to_feature(builtin_entity_label, language):
return "builtinentityfeature%s" % "".join(tokenize_light(
builtin_entity_label.lower(), language))
def _entity_name_to_feature(entity_name, language):
return "entityfeature%s" % "".join(tokenize_light(
entity_name.lower(), language))
def _get_tfidf_vectorizer(language, sublinear_tf=False):
return TfidfVectorizer(tokenizer=lambda x: tokenize_light(x, language),
sublinear_tf=sublinear_tf)
def _get_entity_name_placeholder(entity_label, language):
return "%%%s%%" % "".join(tokenize_light(entity_label, language)).upper()
def _has_any_capitalization(entity_utterances, language):
for utterance in entity_utterances:
tokens = tokenize_light(utterance, language)
if any(t.isupper() or t.istitle() for t in tokens):
return True
return False
def stem_function(text, language):
return get_default_sep(language).join(
[_stem(t) for t in tokenize_light(text, language)])
def capitalize(text, language, resources):
tokens = tokenize_light(text, language)
stop_words = get_stop_words(resources)
return get_default_sep(language).join(
t.title() if t.lower() not in stop_words else t.lower()
for t in tokens)
def _placeholder_fn(self, entity_name):
return "".join(tokenize_light(str(entity_name),
str(self.language))).upper()
def placeholder_fn(x):
return "%%%s%%" % "".join(tokenize_light(x, "en")).upper()
def _init_vectorizer(self, language):
self._tfidf_vectorizer = SklearnTfidfVectorizer(
tokenizer=lambda x: tokenize_light(x, language))
return self
variations.update(flatten(normalization_variations(v) for v in variations))
# We re-generate case variations as normalization can produce new
# variations
if case:
variations.update(flatten(case_variations(v) for v in variations))
if and_:
variations.update(
flatten(and_variations(v, language) for v in variations))
if punctuation:
variations.update(
flatten(punctuation_variations(v, language) for v in variations))
# Special case of number variation which are long to generate due to the
# BuilinEntityParser running on each variation
if numbers:
variations.update(
flatten(
numbers_variations(v, language, builtin_entity_parser)
for v in variations))
# Add single space variations
single_space_variations = set(" ".join(v.split()) for v in variations)
variations.update(single_space_variations)
# Add tokenized variations
tokenized_variations = set(
get_default_sep(language).join(tokenize_light(v, language))
for v in variations)
variations.update(tokenized_variations)
return variations
