def test_tokens_to_indices_uses_pos_tags(self):
tokens = self.tokenizer.tokenize("This is a sentence.")
tokens = [t for t in tokens] + [Token("</S>")]
tokens[1] = Token("is", tag_="VBZ", pos_="VERB")
vocab = Vocabulary()
verb_index = vocab.add_token_to_namespace("VERB", namespace="pos_tags")
cop_index = vocab.add_token_to_namespace("VBZ", namespace="pos_tags")
none_index = vocab.add_token_to_namespace("NONE", namespace="pos_tags")
# Have to add other tokens too, since we're calling `tokens_to_indices` on all of them
vocab.add_token_to_namespace("DET", namespace="pos_tags")
vocab.add_token_to_namespace("NOUN", namespace="pos_tags")
vocab.add_token_to_namespace("PUNCT", namespace="pos_tags")
indexer = PosTagIndexer(namespace="pos_tags", coarse_tags=True)
indices = indexer.tokens_to_indices(tokens, vocab)
assert len(indices) == 1
assert "tokens" in indices
assert indices["tokens"][1] == verb_index
assert indices["tokens"][-1] == none_index
indexer._coarse_tags = False
assert indexer.tokens_to_indices([tokens[1]], vocab) == {
"tokens": [cop_index]
}
def test_tokens_to_indices_uses_pos_tags(self):
tokens = self.tokenizer.split_words(u"This is a sentence.")
tokens = [t for t in tokens] + [Token(u"</S>")]
vocab = Vocabulary()
verb_index = vocab.add_token_to_namespace(u'VERB', namespace=u'pos_tags')
cop_index = vocab.add_token_to_namespace(u'VBZ', namespace=u'pos_tags')
none_index = vocab.add_token_to_namespace(u'NONE', namespace=u'pos_tags')
# Have to add other tokens too, since we're calling `tokens_to_indices` on all of them
vocab.add_token_to_namespace(u'DET', namespace=u'pos_tags')
vocab.add_token_to_namespace(u'NOUN', namespace=u'pos_tags')
vocab.add_token_to_namespace(u'PUNCT', namespace=u'pos_tags')
indexer = PosTagIndexer(coarse_tags=True)
indices = indexer.tokens_to_indices(tokens, vocab, u"tokens")
assert len(indices) == 1
assert u"tokens" in indices
assert indices[u"tokens"][1] == verb_index
assert indices[u"tokens"][-1] == none_index
indexer._coarse_tags = False # pylint: disable=protected-access
assert indexer.tokens_to_indices([tokens[1]], vocab, u"coarse") == {u"coarse": [cop_index]}
def test_tokens_to_indices_uses_pos_tags(self):
tokens = self.tokenizer.split_words("This is a sentence.")
tokens = [t for t in tokens] + [Token("</S>")]
vocab = Vocabulary()
verb_index = vocab.add_token_to_namespace('VERB', namespace='pos_tags')
cop_index = vocab.add_token_to_namespace('VBZ', namespace='pos_tags')
none_index = vocab.add_token_to_namespace('NONE', namespace='pos_tags')
# Have to add other tokens too, since we're calling `tokens_to_indices` on all of them
vocab.add_token_to_namespace('DET', namespace='pos_tags')
vocab.add_token_to_namespace('NOUN', namespace='pos_tags')
vocab.add_token_to_namespace('PUNCT', namespace='pos_tags')
indexer = PosTagIndexer(namespace='pos_tags', coarse_tags=True)
indices = indexer.tokens_to_indices(tokens, vocab, "tokens")
assert len(indices) == 1
assert "tokens" in indices
assert indices["tokens"][1] == verb_index
assert indices["tokens"][-1] == none_index
indexer._coarse_tags = False # pylint: disable=protected-access
assert indexer.tokens_to_indices([tokens[1]], vocab, "coarse") == {"coarse": [cop_index]}
def test_blank_pos_tag(self):
tokens = [Token(token) for token in "allennlp is awesome .".split(" ")]
for token in tokens:
token.pos_ = ""
indexer = PosTagIndexer()
counter = defaultdict(lambda: defaultdict(int))
for token in tokens:
indexer.count_vocab_items(token, counter)
# spacy uses a empty string to indicate "no POS tag"
# we convert it to "NONE"
assert counter["pos_tokens"]["NONE"] == 4
vocab = Vocabulary(counter)
none_index = vocab.get_token_index('NONE', 'pos_tokens')
# should raise no exception
indices = indexer.tokens_to_indices(tokens, vocab, index_name="pos")
assert {"pos": [none_index, none_index, none_index, none_index]} == indices
def test_blank_pos_tag(self):
tokens = [Token(token) for token in "allennlp is awesome .".split(" ")]
indexer = PosTagIndexer()
counter = defaultdict(lambda: defaultdict(int))
for token in tokens:
indexer.count_vocab_items(token, counter)
# spacy uses a empty string to indicate "no POS tag"
# we convert it to "NONE"
assert counter["pos_tokens"]["NONE"] == 4
vocab = Vocabulary(counter)
none_index = vocab.get_token_index("NONE", "pos_tokens")
# should raise no exception
indices = indexer.tokens_to_indices(tokens, vocab)
assert {
"tokens": [none_index, none_index, none_index, none_index]
} == indices
