Python tokenization.FullTokenizer() Examples

The following are 30 code examples of tokenization.FullTokenizer(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module tokenization , or try the search function .
Example #1
Source File: tokenization_test.py    From bert-qa with MIT License 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      if six.PY2:
        vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
      else:
        vocab_writer.write("".join(
            [x + "\n" for x in vocab_tokens]).encode("utf-8"))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #2
Source File: tokenization_test.py    From models with Apache License 2.0 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      if six.PY2:
        vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
      else:
        vocab_writer.write("".join(
            [x + "\n" for x in vocab_tokens]).encode("utf-8"))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #3
Source File: tokenization_test.py    From pynlp with MIT License 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      if six.PY2:
        vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
      else:
        vocab_writer.write("".join(
            [x + "\n" for x in vocab_tokens]).encode("utf-8"))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #4
Source File: tokenization_test.py    From Extending-Google-BERT-as-Question-and-Answering-model-and-Chatbot with Apache License 2.0 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      if six.PY2:
        vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
      else:
        vocab_writer.write("".join(
            [x + "\n" for x in vocab_tokens]).encode("utf-8"))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #5
Source File: tokenization_test.py    From adapter-bert with Apache License 2.0 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      if six.PY2:
        vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
      else:
        vocab_writer.write("".join(
            [x + "\n" for x in vocab_tokens]).encode("utf-8"))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #6
Source File: tokenization_test.py    From models with Apache License 2.0 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      if six.PY2:
        vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
      else:
        vocab_writer.write("".join(
            [x + "\n" for x in vocab_tokens]).encode("utf-8"))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #7
Source File: tokenization_test.py    From training with Apache License 2.0 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      if six.PY2:
        vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
      else:
        vocab_writer.write("".join(
            [x + "\n" for x in vocab_tokens]).encode("utf-8"))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #8
Source File: tokenization_test.py    From BERT with Apache License 2.0 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #9
Source File: tokenization_test.py    From models with Apache License 2.0 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      if six.PY2:
        vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
      else:
        vocab_writer.write("".join(
            [x + "\n" for x in vocab_tokens]).encode("utf-8"))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #10
Source File: tokenization_test.py    From training with Apache License 2.0 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      if six.PY2:
        vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
      else:
        vocab_writer.write("".join(
            [x + "\n" for x in vocab_tokens]).encode("utf-8"))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #11
Source File: tokenization_test.py    From BERT-sentiment--classification with Apache License 2.0 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      if six.PY2:
        vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
      else:
        vocab_writer.write("".join(
            [x + "\n" for x in vocab_tokens]).encode("utf-8"))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #12
Source File: tokenization_test.py    From text_bert_cnn with MIT License 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      if six.PY2:
        vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
      else:
        vocab_writer.write("".join(
            [x + "\n" for x in vocab_tokens]).encode("utf-8"))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #13
Source File: tokenization_test.py    From BERT_STS-B with Apache License 2.0 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #14
Source File: tokenization_test.py    From DeepCT with BSD 3-Clause "New" or "Revised" License 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      if six.PY2:
        vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
      else:
        vocab_writer.write("".join(
            [x + "\n" for x in vocab_tokens]).encode("utf-8"))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #15
Source File: tokenization_test.py    From KBQA-BERT with MIT License 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #16
Source File: tokenization_test.py    From BERT-Classification-Tutorial with Apache License 2.0 6 votes vote down vote up 
def test_full_tokenizer(self):
        vocab_tokens = [
            "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
            "##ing", ","
        ]
        with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
            vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))

            vocab_file = vocab_writer.name

        tokenizer = tokenization.FullTokenizer(vocab_file)
        os.unlink(vocab_file)

        tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
        self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

        self.assertAllEqual(
            tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #17
Source File: tokenization_test.py    From bert_serving with Apache License 2.0 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #18
Source File: tokenization_test.py    From BERT-Chinese-Annotation with Apache License 2.0 6 votes vote down vote up 
def test_full_tokenizer(self):
        vocab_tokens = [
            "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un",
            "runn", "##ing", ","
        ]
        with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
            if six.PY2:
                vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
            else:
                vocab_writer.write("".join(
                    [x + "\n" for x in vocab_tokens]).encode("utf-8"))

            vocab_file = vocab_writer.name

        tokenizer = tokenization.FullTokenizer(vocab_file)
        os.unlink(vocab_file)

        tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
        self.assertAllEqual(tokens,
                            ["un", "##want", "##ed", ",", "runn", "##ing"])

        self.assertAllEqual(
            tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #19
Source File: tokenization_test.py    From bert-multi-gpu with Apache License 2.0 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      if six.PY2:
        vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
      else:
        vocab_writer.write("".join(
            [x + "\n" for x in vocab_tokens]).encode("utf-8"))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #20
Source File: extract_feature.py    From bert-utils with Apache License 2.0 6 votes vote down vote up 
def __init__(self, batch_size=32):
        """
        init BertVector
        :param batch_size:     Depending on your memory default is 32
        """
        self.max_seq_length = args.max_seq_len
        self.layer_indexes = args.layer_indexes
        self.gpu_memory_fraction = 1
        if os.path.exists(args.graph_file):
            self.graph_path = args.graph_file
        else:
            self.graph_path = optimize_graph()

        self.tokenizer = tokenization.FullTokenizer(vocab_file=args.vocab_file, do_lower_case=True)
        self.batch_size = batch_size
        self.estimator = self.get_estimator()
        self.input_queue = Queue(maxsize=1)
        self.output_queue = Queue(maxsize=1)
        self.predict_thread = Thread(target=self.predict_from_queue, daemon=True)
        self.predict_thread.start()
Example #21
Source File: tokenization_test.py    From delft with Apache License 2.0 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      if six.PY2:
        vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
      else:
        vocab_writer.write("".join(
            [x + "\n" for x in vocab_tokens]).encode("utf-8"))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #22
Source File: tokenization_test.py    From gobbli with Apache License 2.0 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      if six.PY2:
        vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
      else:
        vocab_writer.write("".join(
            [x + "\n" for x in vocab_tokens]).encode("utf-8"))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #23
Source File: tokenization_test.py    From curriculum with GNU General Public License v3.0 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #24
Source File: tokenization_test.py    From nlp_research with MIT License 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      if six.PY2:
        vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
      else:
        vocab_writer.write("".join(
            [x + "\n" for x in vocab_tokens]).encode("utf-8"))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #25
Source File: tokenization_test.py    From SIGIR19-BERT-IR with BSD 3-Clause "New" or "Revised" License 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      if six.PY2:
        vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
      else:
        vocab_writer.write("".join(
            [x + "\n" for x in vocab_tokens]).encode("utf-8"))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #26
Source File: tokenization_test.py    From models with MIT License 6 votes vote down vote up 
def test_full_tokenizer(self):
        vocab_tokens = [
            "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
            "##ing", ","
        ]
        with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
            vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))

            vocab_file = vocab_writer.name

        tokenizer = tokenization.FullTokenizer(vocab_file)
        os.unlink(vocab_file)

        tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
        self.assertAllEqual(
            tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

        self.assertAllEqual(
            tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #27
Source File: tokenization_test.py    From bert with Apache License 2.0 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      if six.PY2:
        vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
      else:
        vocab_writer.write("".join(
            [x + "\n" for x in vocab_tokens]).encode("utf-8"))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #28
Source File: tokenization_test.py    From uai-sdk with Apache License 2.0 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      if six.PY2:
        vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
      else:
        vocab_writer.write("".join(
            [x + "\n" for x in vocab_tokens]).encode("utf-8"))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
Example #29
Source File: convert_msmarco_to_tfrecord.py    From dl4ir-doc2query with BSD 3-Clause "New" or "Revised" License 6 votes vote down vote up 
def main(_):
  print('Loading Tokenizer...')
  tokenizer = tokenization.FullTokenizer(
      vocab_file=FLAGS.vocab, do_lower_case=True)

  if not os.path.exists(FLAGS.output_folder):
    os.mkdir(FLAGS.output_folder)

  qrels = None
  if FLAGS.qrels:
    qrels = load_qrels(path=FLAGS.qrels)

  queries = load_queries(path=FLAGS.queries)
  run = load_run(path=FLAGS.run)
  data = merge(qrels=qrels, run=run, queries=queries)

  print('Loading Collection...')
  collection = load_collection(FLAGS.collection_path)

  print('Converting to TFRecord...')
  convert_dataset(data=data, collection=collection, tokenizer=tokenizer)

  print('Done!')
Example #30
Source File: tokenization_test.py    From bert-as-language-model with Apache License 2.0 6 votes vote down vote up 
def test_full_tokenizer(self):
    vocab_tokens = [
        "[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
        "##ing", ","
    ]
    with tempfile.NamedTemporaryFile(delete=False) as vocab_writer:
      vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))

      vocab_file = vocab_writer.name

    tokenizer = tokenization.FullTokenizer(vocab_file)
    os.unlink(vocab_file)

    tokens = tokenizer.tokenize(u"UNwant\u00E9d,running")
    self.assertAllEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])

    self.assertAllEqual(
        tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])