def test_as_array_produces_token_sequence(self): indexer = NerTagIndexer() padded_tokens = indexer.as_padded_tensor_dict( {"tokens": [1, 2, 3, 4, 5]}, {"tokens": 10}) assert padded_tokens["tokens"].tolist() == [ 1, 2, 3, 4, 5, 0, 0, 0, 0, 0 ]
def test_count_vocab_items_uses_ner_tags(self): tokens = self.tokenizer.split_words("Larry Page is CEO of Google.") tokens = [Token("<S>")] + [t for t in tokens] + [Token("</S>")] indexer = NerTagIndexer() counter = defaultdict(lambda: defaultdict(int)) for token in tokens: indexer.count_vocab_items(token, counter) assert counter["ner_tags"] == {'PERSON': 2, 'ORG': 1, 'NONE': 6}
def test_count_vocab_items_uses_ner_tags(self): tokens = self.tokenizer.tokenize("Larry Page is CEO of Google.") tokens = [Token("<S>")] + [t for t in tokens] + [Token("</S>")] indexer = NerTagIndexer() counter = defaultdict(lambda: defaultdict(int)) for token in tokens: indexer.count_vocab_items(token, counter) assert counter["ner_tokens"] == {"PERSON": 2, "ORG": 1, "NONE": 6}
def test_token_to_indices_uses_ner_tags(self): tokens = self.tokenizer.split_words("Larry Page is CEO of Google.") tokens = [t for t in tokens] + [Token("</S>")] vocab = Vocabulary() person_index = vocab.add_token_to_namespace('PERSON', namespace='ner_tags') none_index = vocab.add_token_to_namespace('NONE', namespace='ner_tags') vocab.add_token_to_namespace('ORG', namespace='ner_tags') indexer = NerTagIndexer() assert indexer.token_to_indices(tokens[1], vocab) == person_index assert indexer.token_to_indices(tokens[-1], vocab) == none_index
def test_tokens_to_indices_uses_ner_tags(self): tokens = self.tokenizer.split_words("Larry Page is CEO of Google.") tokens = [t for t in tokens] + [Token("</S>")] vocab = Vocabulary() person_index = vocab.add_token_to_namespace("PERSON", namespace="ner_tags") none_index = vocab.add_token_to_namespace("NONE", namespace="ner_tags") vocab.add_token_to_namespace("ORG", namespace="ner_tags") indexer = NerTagIndexer(namespace="ner_tags") assert indexer.tokens_to_indices([tokens[1]], vocab, "tokens1") == { "tokens1": [person_index] } assert indexer.tokens_to_indices([tokens[-1]], vocab, "tokens-1") == { "tokens-1": [none_index] }
def test_tokens_to_indices_uses_ner_tags(self): tokens = self.tokenizer.split_words(u"Larry Page is CEO of Google.") tokens = [t for t in tokens] + [Token(u"</S>")] vocab = Vocabulary() person_index = vocab.add_token_to_namespace(u'PERSON', namespace=u'ner_tags') none_index = vocab.add_token_to_namespace(u'NONE', namespace=u'ner_tags') vocab.add_token_to_namespace(u'ORG', namespace=u'ner_tags') indexer = NerTagIndexer() assert indexer.tokens_to_indices([tokens[1]], vocab, u"tokens1") == { u"tokens1": [person_index] } assert indexer.tokens_to_indices([tokens[-1]], vocab, u"tokens-1") == { u"tokens-1": [none_index] }
def test_blank_ner_tag(self): tokens = [Token(token) for token in "allennlp is awesome .".split(" ")] for token in tokens: token.ent_type_ = "" indexer = NerTagIndexer() counter = defaultdict(lambda: defaultdict(int)) for token in tokens: indexer.count_vocab_items(token, counter) # spacy uses a empty string to indicate "no NER tag" # we convert it to "NONE" assert counter["ner_tokens"]["NONE"] == 4 vocab = Vocabulary(counter) none_index = vocab.get_token_index('NONE', 'ner_tokens') # should raise no exception indices = indexer.tokens_to_indices(tokens, vocab, index_name="ner") assert {"ner": [none_index, none_index, none_index, none_index]} == indices
def test_blank_ner_tag(self): tokens = [ Token(token)._replace(ent_type_="") for token in "allennlp is awesome .".split(" ") ] indexer = NerTagIndexer() counter = defaultdict(lambda: defaultdict(int)) for token in tokens: indexer.count_vocab_items(token, counter) # spacy uses a empty string to indicate "no NER tag" # we convert it to "NONE" assert counter["ner_tokens"]["NONE"] == 4 vocab = Vocabulary(counter) none_index = vocab.get_token_index("NONE", "ner_tokens") # should raise no exception indices = indexer.tokens_to_indices(tokens, vocab, index_name="ner") assert {"ner": [none_index, none_index, none_index, none_index]} == indices
def __init__(self, word_indexer: Optional[TokenIndexer] = None, is_bert: bool = False, conceptnet_path: Optional[Path] = None): super().__init__(lazy=False) self.pos_indexers = {"pos_tokens": PosTagIndexer()} self.ner_indexers = {"ner_tokens": NerTagIndexer()} self.rel_indexers = { "rel_tokens": SingleIdTokenIndexer(namespace='rel_tokens') } if is_bert: splitter = BertBasicWordSplitter() else: splitter = SpacyWordSplitter() self.tokeniser = WordTokenizer(word_splitter=splitter) self.word_indexers = {'tokens': word_indexer} word_splitter = SpacyWordSplitter(pos_tags=True, ner=True, parse=True) self.word_tokeniser = WordTokenizer(word_splitter=word_splitter) bert_splitter = BertBasicWordSplitter() self.bert_tokeniser = WordTokenizer(word_splitter=bert_splitter) if word_indexer is None: if is_bert: word_indexer = PretrainedBertIndexer( pretrained_model='bert-base-uncased', truncate_long_sequences=False) else: word_indexer = SingleIdTokenIndexer(lowercase_tokens=True) self.word_indexers = {'tokens': word_indexer} self.conceptnet = ConceptNet(conceptnet_path=conceptnet_path)
def test_as_array_produces_token_sequence(self): indexer = NerTagIndexer() padded_tokens = indexer.as_padded_tensor({'key': [1, 2, 3, 4, 5]}, {'key': 10}, {}) assert padded_tokens["key"].tolist() == [1, 2, 3, 4, 5, 0, 0, 0, 0, 0]
def test_padding_functions(self): indexer = NerTagIndexer() assert indexer.get_padding_lengths(0) == {}
def test_as_array_produces_token_sequence(self): indexer = NerTagIndexer() padded_tokens = indexer.pad_token_sequence({'key': [1, 2, 3, 4, 5]}, {'key': 10}, {}) assert padded_tokens == {'key': [1, 2, 3, 4, 5, 0, 0, 0, 0, 0]}
def test_as_array_produces_token_sequence(self): indexer = NerTagIndexer() padded_tokens = indexer.pad_token_sequence([1, 2, 3, 4, 5], 10, {}) assert padded_tokens == [1, 2, 3, 4, 5, 0, 0, 0, 0, 0]
def test_padding_functions(self): indexer = NerTagIndexer() assert indexer.get_padding_token() == 0 assert indexer.get_padding_lengths(0) == {}
validation_dataset_folder = "C:/Users/t-ofarvi/PycharmProjects/UCCA_Dataset_29-06-09/tryout-validation" #"C:/Users/t-ofarvi/Desktop/dev_allen" model_dir = "C:/Users/t-ofarvi/PycharmProjects/tryout-model" vocab_dir = f'{model_dir}/vocabulary' # NOTE: The word tokenizer is a SpaCy tokenizer, which is a little different from the BERT tokenizer. # This was done for convince. word_tokenizer = SpacyMultilingualWhitespaceWordSplitter() bert_indexer = PretrainedBertIndexer(pretrained_model=bert_mode, do_lowercase=bert_do_lowercase, truncate_long_sequences=False) word_indexer = { "bert": bert_indexer, "deps": DepLabelIndexer(namespace="deps_tags"), "ner": NerTagIndexer(), "pos": PosTagIndexer(), "lang": LanguageIndexer() } train_ds, validation_ds = ( UccaSpanParserDatasetReader(word_tokenizer, word_indexer).read(folder) for folder in [train_dataset_folder, validation_dataset_folder]) if os.path.exists(vocab_dir): vocab = Vocabulary.from_files(vocab_dir) else: vocab = Vocabulary.from_instances( itertools.chain(train_ds, validation_ds)) vocab.save_to_files(vocab_dir)