def text_to_instance(
self, # type: ignore
tokens: List[Token],
pos_tags: List[str] = None,
chunk_tags: List[str] = None,
ner_tags: List[str] = None) -> Instance:
"""
We take `pre-tokenized` input here, because we don't have a tokenizer in this class.
"""
# pylint: disable=arguments-differ
sequence = TextField(tokens, self._token_indexers)
instance_fields: Dict[str, Field] = {'tokens': sequence}
instance_fields["metadata"] = MetadataField(
{"words": [x.text for x in tokens]})
# Recode the labels if necessary.
if self.coding_scheme == "BIOUL":
coded_chunks = to_bioul(
chunk_tags) if chunk_tags is not None else None
coded_ner = to_bioul(ner_tags) if ner_tags is not None else None
else:
# the default IOB1
coded_chunks = chunk_tags
coded_ner = ner_tags
# Add "feature labels" to instance
if 'pos' in self.feature_labels:
if pos_tags is None:
raise ConfigurationError(
"Dataset reader was specified to use pos_tags as "
"features. Pass them to text_to_instance.")
instance_fields['pos_tags'] = SequenceLabelField(
pos_tags, sequence, "pos_tags")
if 'chunk' in self.feature_labels:
if coded_chunks is None:
raise ConfigurationError(
"Dataset reader was specified to use chunk tags as "
"features. Pass them to text_to_instance.")
instance_fields['chunk_tags'] = SequenceLabelField(
coded_chunks, sequence, "chunk_tags")
if 'ner' in self.feature_labels:
if coded_ner is None:
raise ConfigurationError(
"Dataset reader was specified to use NER tags as "
" features. Pass them to text_to_instance.")
instance_fields['ner_tags'] = SequenceLabelField(
coded_ner, sequence, "ner_tags")
# Add "tag label" to instance
if self.tag_label == 'ner' and coded_ner is not None:
instance_fields['tags'] = SequenceLabelField(
coded_ner, sequence, self.label_namespace)
elif self.tag_label == 'pos' and pos_tags is not None:
instance_fields['tags'] = SequenceLabelField(
pos_tags, sequence, self.label_namespace)
elif self.tag_label == 'chunk' and coded_chunks is not None:
instance_fields['tags'] = SequenceLabelField(
coded_chunks, sequence, self.label_namespace)
return Instance(instance_fields)
def from_bio_to_bioul(bio_fp: Path, bioul_fp: Path) -> None:
'''
:NOTE: This also removes lines that start with `#` and changes the
Sentiment labels with the following dictionary:
`{'positive': 'POS', 'neutral': 'NEU', 'negative': 'NEG'}`
:param bio_fp: File path to the data that is in CONLL like format:
TOKEN LABEL\n where sentences are split by empty new lines.
The label format is in BIO = Beginning of, inside of,
outside.
:param bioul_fp: File path to save the data that is in `bio_fp` to
this file but in BIOUL
'''
sentiment_tag_convert = {
'positive': 'POS',
'neutral': 'NEU',
'negative': 'NEG'
}
with bioul_fp.open('w+') as bioul_file:
with bio_fp.open('r') as bio_file:
tokens = []
labels = []
for line in bio_file:
if not line.strip():
labels = to_bioul(labels, encoding='BIO')
temp_labels = []
for label in labels:
if len(label.split('-')) == 1:
temp_labels.append(label)
else:
bio_tag, sentiment_tag = label.split('-')
sentiment_tag = sentiment_tag_convert[
sentiment_tag]
temp_labels.append(f'{bio_tag}-{sentiment_tag}')
labels = temp_labels
for token, label in zip(tokens, labels):
bioul_file.write(f'{token} {label}\n')
bioul_file.write('\n')
tokens = []
labels = []
else:
if re.search(r'^#', line):
continue
token, label = line.split()
tokens.append(token)
labels.append(label)
if tokens:
labels = to_bioul(labels, encoding='BIO')
temp_labels = []
for label in labels:
if len(label.split('-')) == 1:
temp_labels.append(label)
else:
bio_tag, sentiment_tag = label.split('-')
sentiment_tag = sentiment_tag_convert[sentiment_tag]
temp_labels.append(f'{bio_tag}-{sentiment_tag}')
labels = temp_labels
for token, label in zip(tokens, labels):
bioul_file.write(f'{token} {label}\n')
def text_to_instance(self, # type: ignore
tokens: List[Token],
pos_tags: List[str] = None,
chunk_tags: List[str] = None,
ner_tags: List[str] = None) -> Instance:
"""
We take `pre-tokenized` input here, because we don't have a tokenizer in this class.
"""
# pylint: disable=arguments-differ
sequence = TextField(tokens, self._token_indexers)
instance_fields: Dict[str, Field] = {'tokens': sequence}
instance_fields["metadata"] = MetadataField({"words": [x.text for x in tokens]})
# Recode the labels if necessary.
if self.coding_scheme == "BIOUL":
coded_chunks = to_bioul(chunk_tags,
encoding=self._original_coding_scheme) if chunk_tags is not None else None
coded_ner = to_bioul(ner_tags,
encoding=self._original_coding_scheme) if ner_tags is not None else None
else:
# the default IOB1
coded_chunks = chunk_tags
coded_ner = ner_tags
# Add "feature labels" to instance
if 'pos' in self.feature_labels:
if pos_tags is None:
raise ConfigurationError("Dataset reader was specified to use pos_tags as "
"features. Pass them to text_to_instance.")
instance_fields['pos_tags'] = SequenceLabelField(pos_tags, sequence, "pos_tags")
if 'chunk' in self.feature_labels:
if coded_chunks is None:
raise ConfigurationError("Dataset reader was specified to use chunk tags as "
"features. Pass them to text_to_instance.")
instance_fields['chunk_tags'] = SequenceLabelField(coded_chunks, sequence, "chunk_tags")
if 'ner' in self.feature_labels:
if coded_ner is None:
raise ConfigurationError("Dataset reader was specified to use NER tags as "
" features. Pass them to text_to_instance.")
instance_fields['ner_tags'] = SequenceLabelField(coded_ner, sequence, "ner_tags")
# Add "tag label" to instance
if self.tag_label == 'ner' and coded_ner is not None:
instance_fields['tags'] = SequenceLabelField(coded_ner, sequence,
self.label_namespace)
elif self.tag_label == 'pos' and pos_tags is not None:
instance_fields['tags'] = SequenceLabelField(pos_tags, sequence,
self.label_namespace)
elif self.tag_label == 'chunk' and coded_chunks is not None:
instance_fields['tags'] = SequenceLabelField(coded_chunks, sequence,
self.label_namespace)
return Instance(instance_fields)
def text_to_instance( # type: ignore
self,
tokens: List[Token],
ner_tags: List[str] = None,
) -> Instance:
"""
We take `pre-tokenized` input here, because we don't have a tokenizer in this class.
"""
sequence = TextField(tokens, self._token_indexers)
instance_fields: Dict[str, Field] = {"tokens": sequence}
# Recode the labels if necessary.
if self.coding_scheme == "BIOUL":
coded_ner = (to_bioul(ner_tags,
encoding=self._original_coding_scheme)
if ner_tags is not None else None)
else:
# the default IOB1
coded_ner = ner_tags
instance_fields["metadata"] = MetadataField({
"words": [x.text for x in tokens],
"tags":
coded_ner
})
instance_fields["tags"] = SequenceLabelField(coded_ner, sequence,
self.label_namespace)
return Instance(instance_fields)
def text_to_instance(
self, # type: ignore
tokens: List[Token],
pos_tags: List[str] = None,
chunk_tags: List[str] = None) -> Instance:
# pylint: disable=arguments-differ
sequence = TextField(tokens, self._token_indexers)
instance_fields: Dict[str, Field] = {'tokens': sequence}
instance_fields["metadata"] = MetadataField(
{"words": [x.text for x in tokens]})
# Recode the labels if necessary.
if self.label_encoding == "BIOUL":
coded_chunks = to_bioul(chunk_tags,
encoding=self._original_label_encoding
) if chunk_tags is not None else None
else:
# the default BIO
coded_chunks = chunk_tags
# Add "feature labels" to instance
if 'pos' in self.feature_labels:
if pos_tags is None:
raise ConfigurationError(
"Dataset reader was specified to use pos_tags as "
"features. Pass them to text_to_instance.")
instance_fields['pos_tags'] = SequenceLabelField(
pos_tags, sequence, "pos_tags")
if 'chunk' in self.feature_labels:
if coded_chunks is None:
raise ConfigurationError(
"Dataset reader was specified to use chunk tags as "
"features. Pass them to text_to_instance.")
instance_fields['chunk_tags'] = SequenceLabelField(
coded_chunks, sequence, "chunk_tags")
# Add "tag label" to instance
if self.tag_label == 'pos' and pos_tags is not None:
instance_fields['tags'] = SequenceLabelField(
pos_tags, sequence, self.label_namespace)
elif self.tag_label == 'chunk' and coded_chunks is not None:
instance_fields['tags'] = SequenceLabelField(
coded_chunks,
sequence,
label_namespace=self._chunk_label_namespace)
return Instance(instance_fields)
def text_to_instance( # type: ignore
self,
tokens: List[Token],
pos_tags: List[str] = None,
chunk_tags: List[str] = None) -> Instance:
"""
We take `pre-tokenized` input here, because we don't have a tokenizer in this class.
"""
sequence = TextField(tokens, self._token_indexers)
instance_fields: Dict[str, Field] = {"tokens": sequence}
instance_fields["metadata"] = MetadataField(
{"words": [x.text for x in tokens]})
# Recode the labels if necessary.
if self.coding_scheme == "BIOUL":
coded_chunks = (to_bioul(chunk_tags,
encoding=self._original_coding_scheme)
if chunk_tags is not None else None)
else:
# the default BIO
coded_chunks = chunk_tags
# Add "feature labels" to instance
if "pos" in self.feature_labels:
if pos_tags is None:
raise ConfigurationError(
"Dataset reader was specified to use pos_tags as "
"features. Pass them to text_to_instance.")
instance_fields["pos_tags"] = SequenceLabelField(
pos_tags, sequence, "pos_tags")
if "chunk" in self.feature_labels:
if coded_chunks is None:
raise ConfigurationError(
"Dataset reader was specified to use chunk tags as "
"features. Pass them to text_to_instance.")
instance_fields["chunk_tags"] = SequenceLabelField(
coded_chunks, sequence, "chunk_tags")
# Add "tag label" to instance
if self.tag_label == "pos" and pos_tags is not None:
instance_fields["tags"] = SequenceLabelField(
pos_tags, sequence, self.label_namespace)
elif self.tag_label == "chunk" and coded_chunks is not None:
instance_fields["tags"] = SequenceLabelField(
coded_chunks, sequence, self.label_namespace)
return Instance(instance_fields)
def text_to_instance(self, # type: ignore
tokens: List[Token],
ner_tags: List[str] = None) -> Instance:
"""
We take `pre-tokenized` input here, because we don't have a tokenizer in this class.
"""
# pylint: disable=arguments-differ
sequence = TextField(tokens, self._token_indexers)
instance_fields: Dict[str, Field] = {'tokens': sequence}
instance_fields["metadata"] = MetadataField({"words": [x.text for x in tokens]})
# Add "tag label" to instance
if ner_tags is not None:
if self._coding_scheme == "BIOUL":
ner_tags = to_bioul(ner_tags, encoding="BIO")
instance_fields['tags'] = SequenceLabelField(ner_tags, sequence)
return Instance(instance_fields)
def offsets_from_tags(
doc: Doc,
tags: List[str],
label_encoding: Optional[str] = "BIOUL",
only_token_spans: bool = False,
) -> List[Dict]:
"""Converts BIOUL or BIO tags to offsets
Parameters
----------
doc
A spaCy Doc created with `text` and the backbone tokenizer
tags
A list of BIOUL or BIO tags
label_encoding
The label encoding of the tags: BIOUL or BIO
only_token_spans
If True, offsets contains only token index references. Default is False
Returns
-------
offsets
A list of dicts with start and end character/token index with respect to the doc and the span label:
`{"start": int, "end": int, "start_token": int, "end_token": int, "label": str}`
"""
# spacy's biluo_tags_to_offsets surprisingly does not check this ...
if len(doc) != len(tags):
raise ValueError(
f"Number of tokens and tags must be the same, "
f"but 'len({list(doc)}) != len({tags})"
)
if label_encoding == "BIO":
tags = to_bioul(tags, encoding="BIO")
offsets = []
for start, end, label in biluo_tags_to_offsets(doc, tags):
span = doc.char_span(start, end)
data = {
"start_token": span.start,
"end_token": span.end,
"label": label,
}
if not only_token_spans:
data.update({"start": start, "end": end})
offsets.append(data)
return offsets
def text_to_instance(self, # type: ignore
tokens: List[Token],
chunk_tags: List[str] = None) -> Instance:
"""
We take `pre-tokenized` input here, because we don't have a tokenizer in this class.
"""
# pylint: disable=arguments-differ
sentence = TextField(tokens, self._token_indexers)
instance_fields: Dict[str, Field] = {'tokens': sentence}
if chunk_tags is None:
return Instance(instance_fields)
chunk_tags = self.clip_chunks_by_max_length(chunk_tags)
# Recode the labels if necessary.
if self.coding_scheme == "BIOUL" and self._original_coding_scheme == "BIO":
chunk_tags = to_bioul(chunk_tags, encoding=self._original_coding_scheme)
# We want to treat O also as a valid span label, which is usually ignored.
# However, each O span needs to be of length 1, since there is no reason to
# combine tokens with O tags as a span, hence replacing O with U-O.
chunk_tags = ['U-O' if tag == 'O' else tag for tag in chunk_tags]
tags, namespace = self.convert_bioul_to_segmental(chunk_tags)
instance_fields["tags"] = SequenceLabelField(tags, sentence, namespace)
seg_starts = []
seg_ends = []
seg_map = []
seg_count = 0
for i, tag in enumerate(chunk_tags):
if tag.startswith('B-') or tag.startswith('U-'):
start = i
seg_starts.append(IndexField(start, sentence))
if tag.startswith('L-') or tag.startswith('U-'):
end = i
assert end - start < self._max_span_width
seg_ends.append(IndexField(end, sentence))
seg_map += [
IndexField(seg_count, instance_fields["tags"]) for _ in range(start, end+1)]
seg_count += 1
instance_fields['seg_ends'] = ListField(seg_ends)
instance_fields['seg_starts'] = ListField(seg_starts)
instance_fields['seg_map'] = ListField(seg_map)
return Instance(instance_fields)
def text_to_instance(
self, # type: ignore
filename: str,
tokens: List[Token],
ner_tags: List[str] = None,
weights: List[float] = None) -> Instance:
"""
We take `pre-tokenized` input here, because we don't have a tokenizer in this class.
"""
# pylint: disable=arguments-differ
sequence = TextField(tokens, self._token_indexers)
instance_fields: Dict[str, Field] = {
'tokens': sequence,
"metadata": MetadataField({"words": [x.text for x in tokens]})
}
if weights is None:
weights = [1.0] * len(tokens)
weight = weights[0]
instance_fields["dataset"] = MetadataField(filename)
# Recode the labels if necessary.
if self.coding_scheme == "BIOUL":
coded_ner = to_bioul(ner_tags,
encoding=self._original_coding_scheme
) if ner_tags is not None else None
else:
# the default IOB1
coded_ner = ner_tags
# Add "feature labels" to instance
if 'ner' in self.feature_labels:
if coded_ner is None:
raise ConfigurationError(
"Dataset reader was specified to use NER tags as "
" features. Pass them to text_to_instance.")
instance_fields['ner_tags'] = SequenceLabelField(
coded_ner, sequence, "ner_tags")
# Add "tag label" to instance
if self.tag_label == 'ner' and coded_ner is not None:
instance_fields['tags'] = SequenceLabelField(
coded_ner, sequence, self.label_namespace)
return Instance(instance_fields)
def text_to_instance(
self, # type: ignore
tokens,
ner_tags=None):
u"""
We take `pre-tokenized` input here, because we don't have a tokenizer in this class.
"""
# pylint: disable=arguments-differ
sequence = TextField(tokens, self._token_indexers)
instance_fields = {u'tokens': sequence}
instance_fields[u"metadata"] = MetadataField(
{u"words": [x.text for x in tokens]})
# Add "tag label" to instance
if ner_tags is not None:
if self._coding_scheme == u"BIOUL":
ner_tags = to_bioul(ner_tags, encoding=u"BIO")
instance_fields[u'tags'] = SequenceLabelField(ner_tags, sequence)
return Instance(instance_fields)
def text_to_instance(
self, # type: ignore
tokens: List[Token],
ner_tags: List[str] = None,
) -> Instance:
"""
We take `pre-tokenized` input here, because we don't have a tokenizer in this class.
"""
sequence = TextField(tokens, self._token_indexers)
instance_fields: Dict[str, Field] = {"tokens": sequence}
instance_fields["metadata"] = MetadataField(
{"words": [x.text for x in tokens]})
# Add "tag label" to instance
if ner_tags is not None:
if self._coding_scheme == "BIOUL":
ner_tags = to_bioul(ner_tags, encoding="BIO")
instance_fields["tags"] = SequenceLabelField(ner_tags, sequence)
return Instance(instance_fields)
def text_to_instance(self,
tokens: List[Token],
tags: Optional[List[str]] = None) -> Instance:
"""
We take `pre-tokenized` input here, because we don't have a tokenizer
in this class.
"""
sequence = TextField(tokens, self._token_indexers)
instance_fields: Dict[str, Field] = {'tokens': sequence}
# Metadata field
metadata_dict = {"words": [x.text for x in tokens]}
instance_fields["metadata"] = MetadataField(metadata_dict)
if tags is not None:
if self.coding_scheme == "BIOUL":
tags = to_bioul(tag_sequence=tags,
encoding=self._original_coding_scheme)
instance_fields['tags'] = SequenceLabelField(
tags, sequence, self.label_namespace)
return Instance(instance_fields)
def text_to_instance(self, # type: ignore
tokens: List[Token],
ner_tags: List[str] = None) -> Instance:
"""
We take `pre-tokenized` input here, because we don't have a tokenizer in this class.
"""
sequence = TextField(tokens, self._token_indexers)
instance_fields: Dict[str, Field] = {'tokens': sequence}
def _remove_BI(_one_tag):
if _one_tag == 'O':
return _one_tag
else:
return _one_tag[2:]
if self.coding_scheme == "BIOUL":
coded_ner = to_bioul(ner_tags,
encoding=self._original_coding_scheme) if ner_tags is not None else None
else:
# the default IOB1
coded_ner = ner_tags
# TODO:
# ner_tags -> spans of NE
# return something like spans, span_labels ("O" if span not in golden_spans, "PER", "LOC"... otherwise)
spans: List[Field] = []
span_labels: List[str] = []
gold_spans: List[Field] = []
gold_span_labels: List[str] = []
assert len(ner_tags) == len(tokens), "sentence:%s but ner_tags:%s"%(str(tokens), str(ner_tags))
ner_gold_spans = _extract_spans(ner_tags) # ner_gold_spans: Dict[tuple(startid, endid), str(entity_type)]
for start, end in enumerate_spans(ner_tags, offset=0, max_span_width=self._max_span_width):
span_labels.append(ner_gold_spans.get((start, end), 'O'))
spans.append(SpanField(start, end, sequence))
pass
_dict_gold_spans = {}
for ky, val in ner_gold_spans.items():
gold_span_labels.append(val)
gold_spans.append(SpanField(ky[0], ky[1], sequence))
if val != 'O':
_dict_gold_spans[ky] = val
pass
instance_fields["metadata"] = MetadataField({"words": [x.text for x in tokens] ,
"gold_spans": _dict_gold_spans})
assert len(spans) == len(span_labels), "span length not equal to span label length..."
span_field = ListField(spans) # a list of (start, end) tuples...
# contains all possible spans and their tags
instance_fields['spans'] = span_field
instance_fields['span_labels'] = SequenceLabelField(span_labels, span_field, "span_tags")
# only contain gold_spans and their tags
# e.g. (0,0,O), (1,1,O), (2,3,PER), (4,4,O) for 'I am Donald Trump .'
gold_span_field = ListField(gold_spans)
instance_fields['gold_spans'] = gold_span_field
instance_fields['gold_span_labels'] = SequenceLabelField(gold_span_labels,
gold_span_field, "span_tags")
# Add "tag label" to instance
if self.tag_label == 'ner' and coded_ner is not None:
instance_fields['tags'] = SequenceLabelField(coded_ner, sequence,
'token_tags')
return Instance(instance_fields)
def text_to_instance(
self, # type: ignore
tokens: List[Token],
pos_tags: List[str] = None,
ner_tags: List[str] = None) -> Instance:
"""
We take `pre-tokenized` input here, because we don't have a tokenizer in this class.
"""
# Recode the labels if necessary.
if self.coding_scheme == "BIOUL":
coded_ner = to_bioul(ner_tags,
encoding=self._original_coding_scheme)
elif self.coding_scheme == "B":
# convert to binary mentions.
coded_ner = ["O" if t == "O" else "U-MNT" for t in ner_tags]
else:
# the default IOB1
coded_ner = ner_tags
fix_coded_ner = []
for t in coded_ner:
if t[-1] == "-":
fix_coded_ner.append("O")
else:
fix_coded_ner.append(t)
coded_ner = fix_coded_ner
# pylint: disable=arguments-differ
sequence = TextField(tokens, self._token_indexers)
words = [x.text for x in tokens]
instance_fields: Dict[str, Field] = {
'tokens':
sequence,
"metadata":
MetadataField({
"words": words,
"orig_tags": coded_ner
}),
"donotuse":
SequenceLabelField(coded_ner, sequence, label_namespace="labels")
}
tag_marginals = []
for tag in coded_ner:
if tag == "O":
if self.strategy == "trust_labels":
# this strategy believes the tags completely
tag_marginal = np.zeros(len(self.alltags)) - 10000
tag_marginal[self.alltags[tag]] = 0
tag_marginals.append(ArrayField(tag_marginal))
elif self.strategy == "uniform":
tag_marginal = np.zeros(len(self.alltags))
tag_marginals.append(ArrayField(tag_marginal))
# this strategy will express ignorance over all possibilities.
else:
raise ConfigurationError("Unknown strategy: " +
self.strategy)
else:
# we always fully trust the given labels.
# this strategy believes the tags completely
tag_marginal = np.zeros(len(self.alltags)) - 10000
tag_marginal[self.alltags[tag]] = 0
tag_marginals.append(ArrayField(tag_marginal))
instance_fields['tags'] = ListField(tag_marginals)
return Instance(instance_fields)
def text_to_instance(
self, # type: ignore
tokens: List[Token],
pos_tags: List[str] = None,
chunk_tags: List[str] = None,
ner_tags: List[str] = None,
target_verb_lemma: str = None,
target_verb_position: int = None,
verb_sense: str = None,
legal_args: List[str] = None,
verb_annotation: List[str] = None,
parse: str = None) -> Instance:
"""
We take `pre-tokenized` input here, because we don't have a tokenizer in this class.
"""
sequence = TextField(tokens, self._token_indexers)
instance_fields: Dict[str, Field] = {'tokens': sequence}
words = [x.text for x in tokens]
instance_fields["metadata"] = MetadataField({
"words": words, # used in ai2's srl model
"pos_tags": pos_tags,
"chunk_tags": chunk_tags,
"ner_tags": chunk_tags,
"target_verb_lemma": target_verb_lemma,
"target_verb_position": target_verb_position,
"verb_annotation": verb_annotation,
"verb_sense": verb_sense,
"legal_args": legal_args,
"verb": target_verb_lemma, # used in ai2's srl model
"parse": parse # for constraints for the dev set srl
})
# This is the position of the gold verb predicate
# We may or may not use it (the model might predict the predicate), but the reader always sends it.
# instance_fields["verb_pos"] = IndexField(index=target_verb_position, sequence_field=sequence)
# TODO Allennlp uses SequenceFeatureField for a indicator vector of the verb position (Find this)
# instance_fields["verb_indicator"] = SequenceFeatureField(index=target_verb_position, sequence_field=sequence)
verb_indicator = np.zeros(len(tokens))
verb_indicator[target_verb_position] = 1.0
instance_fields["verb_indicator"] = ArrayField(array=verb_indicator)
# everyone follows the default IOB2 == BIO format here
coded_srl = get_bio_from_spans(verb_annotation,
year=self.year,
core_args_only=self.core_args_only)
coded_chunks = chunk_tags
coded_ner = ner_tags
if self.coding_scheme == "BIOUL":
# coded_srl = get_bio_from_spans(verb_annotation)
coded_chunks = to_bioul(chunk_tags,
encoding=self._original_coding_scheme
) if chunk_tags is not None else None
coded_ner = to_bioul(ner_tags,
encoding=self._original_coding_scheme
) if ner_tags is not None else None
if 'pos' in self.feature_labels:
if pos_tags is None:
raise ConfigurationError(
"Dataset reader was specified to use pos_tags as "
"features. Pass them to text_to_instance.")
instance_fields['pos_tags'] = SequenceLabelField(
pos_tags, sequence, "pos_tags")
if 'chunk' in self.feature_labels:
if coded_chunks is None:
raise ConfigurationError(
"Dataset reader was specified to use chunk tags as "
"features. Pass them to text_to_instance.")
instance_fields['chunk_tags'] = SequenceLabelField(
coded_chunks, sequence, "chunk_tags")
if 'ner' in self.feature_labels:
if coded_ner is None:
raise ConfigurationError(
"Dataset reader was specified to use NER tags as "
" features. Pass them to text_to_instance.")
instance_fields['ner_tags'] = SequenceLabelField(
coded_ner, sequence, "ner_tags")
# Add "tag label" to instance
if self.tag_label == 'srl' and coded_srl is not None:
instance_fields['tags'] = SequenceLabelField(
coded_srl, sequence, self.label_namespace)
elif self.tag_label == 'pos' and pos_tags is not None:
instance_fields['tags'] = SequenceLabelField(
pos_tags, sequence, self.label_namespace)
elif self.tag_label == 'chunk' and coded_chunks is not None:
instance_fields['tags'] = SequenceLabelField(
coded_chunks, sequence, self.label_namespace)
return Instance(instance_fields)
def _read_dataset(self,
file_path: str,
count_only: bool = False,
keep_idx: Optional[Set[int]] = None):
"""
Yield instances from the file_path.
Parameters
----------
file_path: str, required
The path to the data file.
count_only: bool, optional (default=``False``)
If True, no instances are returned and instead a dummy object is
returned. This is useful for quickly counting the number of instances
in the data file, since creating instances is relatively expensive.
keep_idx: Set[int], optional (default=``None``)
If not None, only yield instances whose index is in this set.
"""
# if `file_path` is a URL, redirect to the cache
file_path = cached_path(file_path)
with open(file_path, "r") as data_file:
if count_only:
logger.info("Counting instances in file at: %s", file_path)
else:
logger.info("Reading instances from lines in file at: %s", file_path)
index = 0
# Group into alternative divider / sentence chunks.
for is_divider, lines in itertools.groupby(data_file, _is_divider):
# Ignore the divider chunks, so that `lines` corresponds to the words
# of a single sentence.
if not is_divider:
if count_only:
yield 1
continue
if keep_idx is not None and index not in keep_idx:
index += 1
continue
fields = [line.strip().split() for line in lines]
# unzipping trick returns tuples, but our Fields need lists
tokens, _, _, ner_tags = [list(field) for field in zip(*fields)]
# Contextualize the tokens if a Contextualizer was provided.
# TODO (nfliu): How can we make this batched?
# Would make contextualizers that use the GPU much faster.
if self._contextualizer:
token_representations = self._contextualizer([tokens])[0]
else:
token_representations = None
# Recode the labels if necessary.
if self._label_encoding == "BIOUL":
coded_ner = to_bioul(ner_tags) if ner_tags is not None else None
else:
coded_ner = ner_tags
yield self.text_to_instance(
tokens,
token_representations,
coded_ner)
index += 1
