Python tokenization.printable_text() Examples

The following are 30 code examples of tokenization.printable_text(). 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: create_pretraining_data.py    From BERT-sentiment--classification with Apache License 2.0 5 votes vote down vote up 
def __str__(self):
    s = ""
    s += "tokens: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.tokens]))
    s += "segment_ids: %s\n" % (" ".join([str(x) for x in self.segment_ids]))
    s += "is_random_next: %s\n" % self.is_random_next
    s += "masked_lm_positions: %s\n" % (" ".join(
        [str(x) for x in self.masked_lm_positions]))
    s += "masked_lm_labels: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.masked_lm_labels]))
    s += "\n"
    return s
Example #2
Source File: create_pretraining_data.py    From training with Apache License 2.0 5 votes vote down vote up 
def __str__(self):
    s = ""
    s += "tokens: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.tokens]))
    s += "segment_ids: %s\n" % (" ".join([str(x) for x in self.segment_ids]))
    s += "is_random_next: %s\n" % self.is_random_next
    s += "masked_lm_positions: %s\n" % (" ".join(
        [str(x) for x in self.masked_lm_positions]))
    s += "masked_lm_labels: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.masked_lm_labels]))
    s += "\n"
    return s
Example #3
Source File: pre.py    From denspi with Apache License 2.0 5 votes vote down vote up 
def __repr__(self):
        s = ""
        s += "qas_id: %s" % (tokenization.printable_text(self.qas_id))
        s += ", question_text: %s" % (
            tokenization.printable_text(self.question_text))
        s += ", doc_tokens: [%s]" % (" ".join(self.doc_tokens))
        if self.start_position:
            s += ", start_position: %d" % (self.start_position)
        if self.start_position:
            s += ", end_position: %d" % (self.end_position)
        return s
Example #4
Source File: run_squad.py    From training with Apache License 2.0 5 votes vote down vote up 
def __repr__(self):
    s = ""
    s += "qas_id: %s" % (tokenization.printable_text(self.qas_id))
    s += ", question_text: %s" % (
        tokenization.printable_text(self.question_text))
    s += ", doc_tokens: [%s]" % (" ".join(self.doc_tokens))
    if self.start_position:
      s += ", start_position: %d" % (self.start_position)
    if self.start_position:
      s += ", end_position: %d" % (self.end_position)
    if self.start_position:
      s += ", is_impossible: %r" % (self.is_impossible)
    return s
Example #5
Source File: run_squad.py    From BERT-for-Sequence-Labeling-and-Text-Classification with Apache License 2.0 5 votes vote down vote up 
def __repr__(self):
    s = ""
    s += "qas_id: %s" % (tokenization.printable_text(self.qas_id))
    s += ", question_text: %s" % (
        tokenization.printable_text(self.question_text))
    s += ", doc_tokens: [%s]" % (" ".join(self.doc_tokens))
    if self.start_position:
      s += ", start_position: %d" % (self.start_position)
    if self.start_position:
      s += ", end_position: %d" % (self.end_position)
    if self.start_position:
      s += ", is_impossible: %r" % (self.is_impossible)
    return s
Example #6
Source File: create_pretraining_data.py    From BERT-for-Sequence-Labeling-and-Text-Classification with Apache License 2.0 5 votes vote down vote up 
def __str__(self):
    s = ""
    s += "tokens: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.tokens]))
    s += "segment_ids: %s\n" % (" ".join([str(x) for x in self.segment_ids]))
    s += "is_random_next: %s\n" % self.is_random_next
    s += "masked_lm_positions: %s\n" % (" ".join(
        [str(x) for x in self.masked_lm_positions]))
    s += "masked_lm_labels: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.masked_lm_labels]))
    s += "\n"
    return s
Example #7
Source File: run_squad.py    From MedicalRelationExtraction with MIT License 5 votes vote down vote up 
def __repr__(self):
    s = ""
    s += "qas_id: %s" % (tokenization.printable_text(self.qas_id))
    s += ", question_text: %s" % (
        tokenization.printable_text(self.question_text))
    s += ", doc_tokens: [%s]" % (" ".join(self.doc_tokens))
    if self.start_position:
      s += ", start_position: %d" % (self.start_position)
    if self.start_position:
      s += ", end_position: %d" % (self.end_position)
    if self.start_position:
      s += ", is_impossible: %r" % (self.is_impossible)
    return s
Example #8
Source File: create_pretraining_data.py    From MedicalRelationExtraction with MIT License 5 votes vote down vote up 
def __str__(self):
    s = ""
    s += "tokens: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.tokens]))
    s += "segment_ids: %s\n" % (" ".join([str(x) for x in self.segment_ids]))
    s += "is_random_next: %s\n" % self.is_random_next
    s += "masked_lm_positions: %s\n" % (" ".join(
        [str(x) for x in self.masked_lm_positions]))
    s += "masked_lm_labels: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.masked_lm_labels]))
    s += "\n"
    return s
Example #9
Source File: create_pretraining_data.py    From BERT-multi-gpu with Apache License 2.0 5 votes vote down vote up 
def __str__(self):
    s = ""
    s += "tokens: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.tokens]))
    s += "segment_ids: %s\n" % (" ".join([str(x) for x in self.segment_ids]))
    s += "is_random_next: %s\n" % self.is_random_next
    s += "masked_lm_positions: %s\n" % (" ".join(
        [str(x) for x in self.masked_lm_positions]))
    s += "masked_lm_labels: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.masked_lm_labels]))
    s += "\n"
    return s
Example #10
Source File: create_pretraining_data.py    From project-purifier with Apache License 2.0 5 votes vote down vote up 
def __str__(self):
    s = ""
    s += "tokens: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.tokens]))
    s += "segment_ids: %s\n" % (" ".join([str(x) for x in self.segment_ids]))
    s += "is_random_next: %s\n" % self.is_random_next
    s += "masked_lm_positions: %s\n" % (" ".join(
        [str(x) for x in self.masked_lm_positions]))
    s += "masked_lm_labels: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.masked_lm_labels]))
    s += "\n"
    return s
Example #11
Source File: run_squad.py    From coref with Apache License 2.0 5 votes vote down vote up 
def __repr__(self):
    s = ""
    s += "qas_id: %s" % (tokenization.printable_text(self.qas_id))
    s += ", question_text: %s" % (
        tokenization.printable_text(self.question_text))
    s += ", doc_tokens: [%s]" % (" ".join(self.doc_tokens))
    if self.start_position:
      s += ", start_position: %d" % (self.start_position)
    if self.start_position:
      s += ", end_position: %d" % (self.end_position)
    if self.start_position:
      s += ", is_impossible: %r" % (self.is_impossible)
    return s
Example #12
Source File: create_pretraining_data.py    From coref with Apache License 2.0 5 votes vote down vote up 
def __str__(self):
    s = ""
    s += "tokens: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.tokens]))
    s += "segment_ids: %s\n" % (" ".join([str(x) for x in self.segment_ids]))
    s += "is_random_next: %s\n" % self.is_random_next
    s += "masked_lm_positions: %s\n" % (" ".join(
        [str(x) for x in self.masked_lm_positions]))
    s += "masked_lm_labels: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.masked_lm_labels]))
    s += "\n"
    return s
Example #13
Source File: create_pretraining_data.py    From albert-chinese-ner with MIT License 5 votes vote down vote up 
def __str__(self):
    s = ""
    s += "tokens: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.tokens]))
    s += "segment_ids: %s\n" % (" ".join([str(x) for x in self.segment_ids]))
    s += "is_random_next: %s\n" % self.is_random_next
    s += "masked_lm_positions: %s\n" % (" ".join(
        [str(x) for x in self.masked_lm_positions]))
    s += "masked_lm_labels: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.masked_lm_labels]))
    s += "\n"
    return s
Example #14
Source File: create_pretraining_data.py    From ALBERT-TF2.0 with Apache License 2.0 5 votes vote down vote up 
def __str__(self):
    s = ""
    s += "tokens: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.tokens]))
    s += "segment_ids: %s\n" % (" ".join([str(x) for x in self.segment_ids]))
    s += "token_boundary: %s\n" % (" ".join(
        [str(x) for x in self.token_boundary]))
    s += "is_random_next: %s\n" % self.is_random_next
    s += "masked_lm_positions: %s\n" % (" ".join(
        [str(x) for x in self.masked_lm_positions]))
    s += "masked_lm_labels: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.masked_lm_labels]))
    s += "\n"
    return s
Example #15
Source File: create_pretraining_data.py    From MAX-Text-Sentiment-Classifier with Apache License 2.0 5 votes vote down vote up 
def __str__(self):
        s = ""
        s += "tokens: %s\n" % (" ".join(
            [tokenization.printable_text(x) for x in self.tokens]))
        s += "segment_ids: %s\n" % (" ".join([str(x) for x in self.segment_ids]))
        s += "is_random_next: %s\n" % self.is_random_next
        s += "masked_lm_positions: %s\n" % (" ".join(
            [str(x) for x in self.masked_lm_positions]))
        s += "masked_lm_labels: %s\n" % (" ".join(
            [tokenization.printable_text(x) for x in self.masked_lm_labels]))
        s += "\n"
        return s
Example #16
Source File: squad_lib.py    From ALBERT-TF2.0 with Apache License 2.0 5 votes vote down vote up 
def __repr__(self):
    s = ""
    s += "qas_id: %s" % (tokenization.printable_text(self.qas_id))
    s += ", question_text: %s" % (
        tokenization.printable_text(self.question_text))
    s += ", paragraph_text: [%s]" % (" ".join(self.paragraph_text))
    if self.start_position:
      s += ", start_position: %d" % (self.start_position)
    if self.start_position:
      s += ", end_position: %d" % (self.end_position)
    if self.start_position:
      s += ", is_impossible: %r" % (self.is_impossible)
    return s
Example #17
Source File: run_squad.py    From BERT-sentiment--classification with Apache License 2.0 5 votes vote down vote up 
def __repr__(self):
    s = ""
    s += "qas_id: %s" % (tokenization.printable_text(self.qas_id))
    s += ", question_text: %s" % (
        tokenization.printable_text(self.question_text))
    s += ", doc_tokens: [%s]" % (" ".join(self.doc_tokens))
    if self.start_position:
      s += ", start_position: %d" % (self.start_position)
    if self.start_position:
      s += ", end_position: %d" % (self.end_position)
    if self.start_position:
      s += ", is_impossible: %r" % (self.is_impossible)
    return s
Example #18
Source File: run_squad.py    From QGforQA with MIT License 5 votes vote down vote up 
def __repr__(self):
    s = ""
    s += "qas_id: %s" % (tokenization.printable_text(self.qas_id))
    s += ", question_text: %s" % (
        tokenization.printable_text(self.question_text))
    s += ", doc_tokens: [%s]" % (" ".join(self.doc_tokens))
    if self.start_position:
      s += ", start_position: %d" % (self.start_position)
    if self.start_position:
      s += ", end_position: %d" % (self.end_position)
    if self.start_position:
      s += ", is_impossible: %r" % (self.is_impossible)
    return s
Example #19
Source File: create_pretraining_data.py    From BERT_STS-B with Apache License 2.0 5 votes vote down vote up 
def __str__(self):
    s = ""
    s += "tokens: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.tokens]))
    s += "segment_ids: %s\n" % (" ".join([str(x) for x in self.segment_ids]))
    s += "is_random_next: %s\n" % self.is_random_next
    s += "masked_lm_positions: %s\n" % (" ".join(
        [str(x) for x in self.masked_lm_positions]))
    s += "masked_lm_labels: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.masked_lm_labels]))
    s += "\n"
    return s
Example #20
Source File: run_squad.py    From BERT_STS-B with Apache License 2.0 5 votes vote down vote up 
def __repr__(self):
    s = ""
    s += "qas_id: %s" % (tokenization.printable_text(self.qas_id))
    s += ", question_text: %s" % (
        tokenization.printable_text(self.question_text))
    s += ", doc_tokens: [%s]" % (" ".join(self.doc_tokens))
    if self.start_position:
      s += ", start_position: %d" % (self.start_position)
    if self.start_position:
      s += ", end_position: %d" % (self.end_position)
    return s
Example #21
Source File: create_pretraining_data.py    From KBQA-BERT with MIT License 5 votes vote down vote up 
def __str__(self):
    s = ""
    s += "tokens: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.tokens]))
    s += "segment_ids: %s\n" % (" ".join([str(x) for x in self.segment_ids]))
    s += "is_random_next: %s\n" % self.is_random_next
    s += "masked_lm_positions: %s\n" % (" ".join(
        [str(x) for x in self.masked_lm_positions]))
    s += "masked_lm_labels: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.masked_lm_labels]))
    s += "\n"
    return s
Example #22
Source File: run_squad.py    From KBQA-BERT with MIT License 5 votes vote down vote up 
def __repr__(self):
    s = ""
    s += "qas_id: %s" % (tokenization.printable_text(self.qas_id))
    s += ", question_text: %s" % (
        tokenization.printable_text(self.question_text))
    s += ", doc_tokens: [%s]" % (" ".join(self.doc_tokens))
    if self.start_position:
      s += ", start_position: %d" % (self.start_position)
    if self.start_position:
      s += ", end_position: %d" % (self.end_position)
    if self.start_position:
      s += ", is_impossible: %r" % (self.is_impossible)
    return s
Example #23
Source File: create_pretraining_data.py    From bert-qa with MIT License 5 votes vote down vote up 
def __str__(self):
    s = ""
    s += "tokens: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.tokens]))
    s += "segment_ids: %s\n" % (" ".join([str(x) for x in self.segment_ids]))
    s += "is_random_next: %s\n" % self.is_random_next
    s += "masked_lm_positions: %s\n" % (" ".join(
        [str(x) for x in self.masked_lm_positions]))
    s += "masked_lm_labels: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.masked_lm_labels]))
    s += "\n"
    return s
Example #24
Source File: run_squad.py    From bert-qa with MIT License 5 votes vote down vote up 
def __repr__(self):
    s = ""
    s += "qas_id: %s" % (tokenization.printable_text(self.qas_id))
    s += ", question_text: %s" % (
        tokenization.printable_text(self.question_text))
    s += ", doc_tokens: [%s]" % (" ".join(self.doc_tokens))
    if self.start_position:
      s += ", start_position: %d" % (self.start_position)
    if self.start_position:
      s += ", end_position: %d" % (self.end_position)
    if self.start_position:
      s += ", is_impossible: %r" % (self.is_impossible)
    return s
Example #25
Source File: run_squad_v2.py    From bert-qa with MIT License 5 votes vote down vote up 
def __repr__(self):
        s = ""
        s += "qas_id: %s" % (tokenization.printable_text(self.qas_id))
        s += ", question_text: %s" % (tokenization.printable_text(self.question_text))
        s += ", doc_tokens: [%s]" % (" ".join(self.doc_tokens))
        if self.start_position:
            s += ", start_position: %d" % (self.start_position)
        if self.start_position:
            s += ", end_position: %d" % (self.end_position)
        if self.start_position:
            s += ", is_impossible: %r" % (self.is_impossible)
        return s
Example #26
Source File: create_pretraining_data.py    From delft with Apache License 2.0 5 votes vote down vote up 
def __str__(self):
    s = ""
    s += "tokens: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.tokens]))
    s += "segment_ids: %s\n" % (" ".join([str(x) for x in self.segment_ids]))
    s += "is_random_next: %s\n" % self.is_random_next
    s += "masked_lm_positions: %s\n" % (" ".join(
        [str(x) for x in self.masked_lm_positions]))
    s += "masked_lm_labels: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.masked_lm_labels]))
    s += "\n"
    return s
Example #27
Source File: run_squad.py    From delft with Apache License 2.0 5 votes vote down vote up 
def __repr__(self):
    s = ""
    s += "qas_id: %s" % (tokenization.printable_text(self.qas_id))
    s += ", question_text: %s" % (
        tokenization.printable_text(self.question_text))
    s += ", doc_tokens: [%s]" % (" ".join(self.doc_tokens))
    if self.start_position:
      s += ", start_position: %d" % (self.start_position)
    if self.start_position:
      s += ", end_position: %d" % (self.end_position)
    if self.start_position:
      s += ", is_impossible: %r" % (self.is_impossible)
    return s
Example #28
Source File: create_pretraining_data.py    From uai-sdk with Apache License 2.0 5 votes vote down vote up 
def __str__(self):
    s = ""
    s += "tokens: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.tokens]))
    s += "segment_ids: %s\n" % (" ".join([str(x) for x in self.segment_ids]))
    s += "is_random_next: %s\n" % self.is_random_next
    s += "masked_lm_positions: %s\n" % (" ".join(
        [str(x) for x in self.masked_lm_positions]))
    s += "masked_lm_labels: %s\n" % (" ".join(
        [tokenization.printable_text(x) for x in self.masked_lm_labels]))
    s += "\n"
    return s
Example #29
Source File: run_squad.py    From uai-sdk with Apache License 2.0 5 votes vote down vote up 
def __repr__(self):
    s = ""
    s += "qas_id: %s" % (tokenization.printable_text(self.qas_id))
    s += ", question_text: %s" % (
        tokenization.printable_text(self.question_text))
    s += ", doc_tokens: [%s]" % (" ".join(self.doc_tokens))
    if self.start_position:
      s += ", start_position: %d" % (self.start_position)
    if self.start_position:
      s += ", end_position: %d" % (self.end_position)
    if self.start_position:
      s += ", is_impossible: %r" % (self.is_impossible)
    return s
Example #30
Source File: run_squad.py    From BERT-for-Chinese-Question-Answering with Apache License 2.0 5 votes vote down vote up 
def __repr__(self):
        s = ""
        s += "qas_id: %s" % (tokenization.printable_text(self.qas_id))
        s += ", question_text: %s" % (
            tokenization.printable_text(self.question_text))
        s += ", doc_tokens: [%s]" % (" ".join(self.doc_tokens))
        if self.start_position:
            s += ", start_position: %d" % (self.start_position)
        if self.start_position:
            s += ", end_position: %d" % (self.end_position)
        return s