Python fields.LabelField方法代码示例

# 需要导入模块: from allennlp.data import fields [as 别名]
# 或者: from allennlp.data.fields import LabelField [as 别名]
def text_to_instance(self,  # type: ignore
                         tokens: List[str],
                         entity_1: Tuple[int],
                         entity_2: Tuple[int],
                         label: str = None) -> Instance:
        # pylint: disable=arguments-differ
        fields: Dict[str, Field] = {}
        
        tokens = [OpenAISplitter._standardize(token) for token in tokens]
        tokens = ['__start__'] + tokens[entity_1[0]:entity_1[1]+1] + ['__del1__'] + tokens[entity_2[0]:entity_2[1]+1] + ['__del2__'] + tokens + ['__clf__']
            
        sentence = TextField([Token(text=t) for t in tokens], self._token_indexers)
        fields['sentence'] = sentence
        #fields['entity1'] = SpanField(*entity_1, sequence_field=sentence)
        #fields['entity2'] = SpanField(*entity_2, sequence_field=sentence)
        
        if label:
            fields['label'] = LabelField(label)

        return Instance(fields) 

# 需要导入模块: from allennlp.data import fields [as 别名]
# 或者: from allennlp.data.fields import LabelField [as 别名]
def text_to_instance(self, tokens: List[Token], tags: List[str] = None, domain: str = None,
        intent: str = None, dialog_act: Dict[str, Any] = None) -> Instance:  # type: ignore
        """
        We take `pre-tokenized` input here, because we don't have a tokenizer in this class.
        """
        # pylint: disable=arguments-differ
        fields: Dict[str, Field] = {}
        sequence = TextField(tokens, self._token_indexers)
        fields["tokens"] = sequence
        if tags:
            fields["tags"] = SequenceLabelField(tags, sequence)
        if domain:
            fields["domain"] = LabelField(domain, label_namespace="domain_labels")
        if intent:
            fields["intent"] = LabelField(intent, label_namespace="intent_labels")
        if dialog_act is not None:
            fields["metadata"] = MetadataField({"words": [x.text for x in tokens],
            'dialog_act': dialog_act})
        else:
            fields["metadata"] = MetadataField({"words": [x.text for x in tokens], 'dialog_act': {}})
        return Instance(fields) 

# 需要导入模块: from allennlp.data import fields [as 别名]
# 或者: from allennlp.data.fields import LabelField [as 别名]
def text_to_instance(self, query_id:str, doc_id:str, query_sequence: str, doc_sequence: str) -> Instance:  # type: ignore
        # pylint: disable=arguments-differ

        query_id_field = LabelField(int(query_id), skip_indexing=True)
        doc_id_field = LabelField(int(doc_id), skip_indexing=True)

        query_tokenized = self._tokenizer.tokenize(query_sequence)
        if self.max_query_length > -1:
            query_tokenized = query_tokenized[:self.max_query_length]

        query_field = TextField(query_tokenized, self._token_indexers)
        
        doc_tokenized = self._tokenizer.tokenize(doc_sequence)
        if self.max_doc_length > -1:
            doc_tokenized = doc_tokenized[:self.max_doc_length]

        doc_field = TextField(doc_tokenized, self._token_indexers)

        return Instance({
            "query_id":query_id_field,
            "doc_id":doc_id_field,
            "query_tokens":query_field,
            "doc_tokens":doc_field}) 

# 需要导入模块: from allennlp.data import fields [as 别名]
# 或者: from allennlp.data.fields import LabelField [as 别名]
def text_to_instance(self,  # type: ignore
                         item_id: Any,
                         question_text: str,
                         choice_text_list: List[str],
                         answer_id: int
                         ) -> Instance:
        # pylint: disable=arguments-differ
        fields: Dict[str, Field] = {}
        question_tokens = self._tokenizer.tokenize(question_text)
        choices_tokens_list = [self._tokenizer.tokenize(x) for x in choice_text_list]
        fields['question'] = TextField(question_tokens, self._token_indexers)
        fields['choices_list'] = ListField([TextField(x, self._token_indexers) for x in choices_tokens_list])
        fields['label'] = LabelField(answer_id, skip_indexing=True)

        metadata = {
            "id": item_id,
            "question_text": question_text,
            "choice_text_list": choice_text_list,
            "question_tokens": [x.text for x in question_tokens],
            "choice_tokens_list": [[x.text for x in ct] for ct in choices_tokens_list],
        }

        fields["metadata"] = MetadataField(metadata)

        return Instance(fields) 

# 需要导入模块: from allennlp.data import fields [as 别名]
# 或者: from allennlp.data.fields import LabelField [as 别名]
def test_duplicate(self):
        # Verify the `duplicate()` method works with a `PretrainedTransformerIndexer` in
        # a `TextField`. See https://github.com/allenai/allennlp/issues/4270.
        instance = Instance(
            {
                "words": TextField(
                    [Token("hello")], {"tokens": PretrainedTransformerIndexer("bert-base-uncased")}
                )
            }
        )

        other = instance.duplicate()
        assert other == instance

        # Adding new fields to the original instance should not effect the duplicate.
        instance.add_field("labels", LabelField("some_label"))
        assert "labels" not in other.fields
        assert other != instance  # sanity check on the '__eq__' method. 

# 需要导入模块: from allennlp.data import fields [as 别名]
# 或者: from allennlp.data.fields import LabelField [as 别名]
def text_to_instance(self,
                         premise: str,
                         hypothesis: str,
                         hypothesis_structure: str,
                         label: str = None) -> Instance:
        fields: Dict[str, Field] = {}
        premise_tokens = self._tokenizer.tokenize(premise)[-self._max_tokens:]
        hypothesis_tokens = self._tokenizer.tokenize(hypothesis)[-self._max_tokens:]

        fields['premise'] = TextField(premise_tokens, self._token_indexers)
        fields['hypothesis'] = TextField(hypothesis_tokens, self._token_indexers)
        metadata = {
            'premise': premise,
            'hypothesis': hypothesis,
            'premise_tokens': [token.text for token in premise_tokens],
            'hypothesis_tokens': [token.text for token in hypothesis_tokens]
        }
        fields['metadata'] = MetadataField(metadata)
        self._add_structure_to_fields(hypothesis_structure, fields)
        if label:
            fields['label'] = LabelField(label)
        return Instance(fields) 

# 需要导入模块: from allennlp.data import fields [as 别名]
# 或者: from allennlp.data.fields import LabelField [as 别名]
def text_to_instance(self,  # type: ignore
                         premise: str,
                         hypothesis: str,
                         pid: str = None,
                         label: str = None) -> Instance:

        fields: Dict[str, Field] = {}

        premise_tokens = [Token(t) for t in premise.split(' ')]  # Removing code for parentheses in NLI
        hypothesis_tokens = [Token(t) for t in hypothesis.split(' ')]

        if self.max_l is not None:
            premise_tokens = premise_tokens[:self.max_l]
            hypothesis_tokens = hypothesis_tokens[:self.max_l]

        fields['premise'] = TextField(premise_tokens, self._token_indexers)
        fields['hypothesis'] = TextField(hypothesis_tokens, self._token_indexers)

        if label:
            fields['selection_label'] = LabelField(label, label_namespace='selection_labels')

        if pid:
            fields['pid'] = IdField(pid)

        return Instance(fields) 

# 需要导入模块: from allennlp.data import fields [as 别名]
# 或者: from allennlp.data.fields import LabelField [as 别名]
def text_to_instance(self,  # type: ignore
                         premise: str,
                         hypothesis: str,
                         pid: str = None,
                         label: str = None) -> Instance:

        fields: Dict[str, Field] = {}

        premise_tokens = [Token(t) for t in premise.split(' ')]  # Removing code for parentheses in NLI
        hypothesis_tokens = [Token(t) for t in hypothesis.split(' ')]

        if self.max_l is not None:
            premise_tokens = premise_tokens[:self.max_l]
            hypothesis_tokens = hypothesis_tokens[:self.max_l]

        fields['premise'] = TextField(premise_tokens, self._token_indexers)
        fields['hypothesis'] = TextField(hypothesis_tokens, self._token_indexers)

        if label:
            fields['label'] = LabelField(label, label_namespace='labels')

        if pid:
            fields['pid'] = IdField(pid)

        return Instance(fields) 

# 需要导入模块: from allennlp.data import fields [as 别名]
# 或者: from allennlp.data.fields import LabelField [as 别名]
def text_to_instance(self,  # type: ignore
                         premise     ,
                         hypothesis     ,
                         label      = None)            :
        # pylint: disable=arguments-differ
        fields                   = {}
        premise_tokens = self._tokenizer.tokenize(premise)
        hypothesis_tokens = self._tokenizer.tokenize(hypothesis)
        fields[u'premise'] = TextField(premise_tokens, self._token_indexers)
        fields[u'hypothesis'] = TextField(hypothesis_tokens, self._token_indexers)
        if label:
            fields[u'label'] = LabelField(label)

        metadata = {u"premise_tokens": [x.text for x in premise_tokens],
                    u"hypothesis_tokens": [x.text for x in hypothesis_tokens]}
        fields[u"metadata"] = MetadataField(metadata)
        return Instance(fields) 

# 需要导入模块: from allennlp.data import fields [as 别名]
# 或者: from allennlp.data.fields import LabelField [as 别名]
def text_to_instance(self,  # type: ignore
                         sentence_tokens: List[str],
                         verb_vector: List[int],
                         entity_vector: List[int],
                         state_change_types: Optional[List[str]] = None,
                         state_change_tags: Optional[List[str]] = None) -> Instance:
        # pylint: disable=arguments-differ
        fields: Dict[str, Field] = {}

        # encode inputs
        token_field = TextField([Token(word) for word in sentence_tokens], self._token_indexers)
        fields['tokens'] = token_field
        fields['verb_span'] = SequenceLabelField(verb_vector, token_field, 'indicator_tags')
        fields['entity_span'] = SequenceLabelField(entity_vector, token_field, 'indicator_tags')

        # encode outputs
        if state_change_types:
            fields['state_change_type_labels'] = LabelField(state_change_types, 'state_change_type_labels')
        if state_change_tags:
            fields['state_change_tags'] = SequenceLabelField(state_change_tags, token_field, 'state_change_tags')

        return Instance(fields) 

# 需要导入模块: from allennlp.data import fields [as 别名]
# 或者: from allennlp.data.fields import LabelField [as 别名]
def text_to_instance(
        self,  # type: ignore
        query: List[str],
        slot_tags: List[str] = None,
        sql_template: str = None,
    ) -> Instance:
        fields: Dict[str, Field] = {}
        tokens = TextField([Token(t) for t in query], self._token_indexers)
        fields["tokens"] = tokens

        if slot_tags is not None and sql_template is not None:
            slot_field = SequenceLabelField(slot_tags, tokens, label_namespace="slot_tags")
            template = LabelField(sql_template, label_namespace="template_labels")
            fields["slot_tags"] = slot_field
            fields["template"] = template

        return Instance(fields) 

# 需要导入模块: from allennlp.data import fields [as 别名]
# 或者: from allennlp.data.fields import LabelField [as 别名]
def text_to_instance(self, # pylint: disable=arguments-differ
                         premise: str,
                         hypothesis: str,
                         label: str = None) -> Instance:
        fields: Dict[str, Field] = {}
        premise_tokens = [Token(token.text)
                          for token in self._tokenizer.tokenize(premise)[-self._max_tokens:]]
        hypothesis_tokens = [Token(token.text)
                             for token in self._tokenizer.tokenize(hypothesis)[-self._max_tokens:]]

        fields['premise'] = TextField(premise_tokens, self._token_indexers)
        fields['hypothesis'] = TextField(hypothesis_tokens, self._token_indexers)

        if label:
            fields['label'] = LabelField(label)

        # metadata = {"premise_tokens": [x.text for x in premise_tokens],
        #             "hypothesis_tokens": [x.text for x in hypothesis_tokens]}
        # fields["metadata"] = MetadataField(metadata)
        return Instance(fields) 

# 需要导入模块: from allennlp.data import fields [as 别名]
# 或者: from allennlp.data.fields import LabelField [as 别名]
def text_to_instance(self,
                         citation_text: str,
                         citing_paper_id: str,
                         cited_paper_id: str,
                         intent: List[str] = None,
                         venue: str = None,
                         section_name: str = None) -> Instance:

        citation_tokens = self._tokenizer.tokenize(citation_text)

        fields = {
            'citation_text': TextField(citation_tokens, self._token_indexers),
        }

        if section_name is not None:
            fields['section_label'] = LabelField(section_name, label_namespace="section_labels")
        fields['citing_paper_id'] = MetadataField(citing_paper_id)
        fields['cited_paper_id'] = MetadataField(cited_paper_id)
        return Instance(fields) 

# 需要导入模块: from allennlp.data import fields [as 别名]
# 或者: from allennlp.data.fields import LabelField [as 别名]
def text_to_instance(self,
                         citation_text: str,
                         citing_paper_id: str,
                         cited_paper_id: str,
                         intent: List[str] = None,
                         section_name: str = None) -> Instance:

        citation_tokens = self._tokenizer.tokenize(citation_text)

        fields = {
            'citation_text': TextField(citation_tokens, self._token_indexers),
        }

        if section_name is not None:
            fields['section_label'] = LabelField(section_name, label_namespace="section_labels")

        fields['citing_paper_id'] = MetadataField(citing_paper_id)
        fields['cited_paper_id'] = MetadataField(cited_paper_id)
        return Instance(fields) 

# 需要导入模块: from allennlp.data import fields [as 别名]
# 或者: from allennlp.data.fields import LabelField [as 别名]
def text_to_instance(self,  # type: ignore
                         premise: str,
                         hypotheses: List[str],
                         label: int = None) -> Instance:
        # pylint: disable=arguments-differ
        fields: Dict[str, Field] = {}
        premise_tokens = self._tokenizer.tokenize(premise)
        fields['premise'] = TextField(premise_tokens, self._token_indexers)

        # This could be another way to get randomness
        for i, hyp in enumerate(hypotheses):
            hypothesis_tokens = self._tokenizer.tokenize(hyp)
            fields['hypothesis{}'.format(i)] = TextField(hypothesis_tokens, self._token_indexers)

        if label is not None:
            fields['label'] = LabelField(label, skip_indexing=True)
        return Instance(fields)